Artificial Intelligence Review (2022) 55:5731–5780

https://doi.org/10.1007/s10462-022-10144-1

A survey on sentiment analysis methods, applications,

and challenges

Mayur Wankhade1,2 · Annavarapu Chandra Sekhara Rao1,2   · Chaitanya Kulkarni1,2

Published online: 7 February 2022

© The Author(s), under exclusive licence to Springer Nature B.V. 2022

Abstract
The rapid growth of Internet-based applications, such as social media platforms and blogs,
has resulted in comments and reviews concerning day-to-day activities. Sentiment analy-
sis is the process of gathering and analyzing people’s opinions, thoughts, and impressions
regarding various topics, products, subjects, and services. People’s opinions can be benefi-
cial to corporations, governments, and individuals for collecting information and making
decisions based on opinion. However, the sentiment analysis and evaluation procedure face
numerous challenges. These challenges create impediments to accurately interpreting sen-
timents and determining the appropriate sentiment polarity. Sentiment analysis identifies
and extracts subjective information from the text using natural language processing and
text mining. This article discusses a complete overview of the method for completing this
task as well as the applications of sentiment analysis. Then, it evaluates, compares, and
investigates the approaches used to gain a comprehensive understanding of their advan-
tages and disadvantages. Finally, the challenges of sentiment analysis are examined in
order to define future directions.

Keywords  Sentiment analysis · Text analysis · Word embedding · Machine learning ·

Social media

1 Introduction

Sentiment analysis has gained widespread acceptance in recent years, not just among
researchers but also among businesses, governments, and organizations (Sánchez-Rada
and Iglesias 2019). The growing popularity of the Internet has lifted the web to the
rank of the principal source of universal information. Lots of users use various online
resources to express their views and opinions. To constantly monitor public opinion and

* Annavarapu Chandra Sekhara Rao

[email protected]
Mayur Wankhade
[email protected]
1
Department of Computer Science and Engineering, Indian Institute of Technology (ISM),
Dhanbad 826004, India
2
Dayananda Sagar College of Engineering, Bangalore 560078, India

13
Vol.:(0123456789)
 5732 M. Wankhade et al.

aid decision-making, we must employ user-generated data to analyze it automatically.

As a result, sentiment analysis has increased its popularity across research communities
in recent years. Sentiment analysis is also called as Opinion analysis or Opinion mining.
We have seen a recent growth in the sentiment analysis task. The variuos research works
in sentiment analysis  (Ligthart et  al. 2021) published an overview on Opinion mining
in the earlier stage. In (Piryani et al. 2017) discusses the study topic from 2000 to 2015
and provides a framework for computationally processing unstructured data with the
primary goal of extracting views and identifying their moods. Several recent surveys
(Yousif et al. 2019; Birjali et al. 2021) authors has described the problem of sentiment
analysis and suggested potential directions. Soleymani et  al. (2017) and Yadav and
Vishwakarma (2020) on sentiment classification have been published. Also the topic
of detecting opinion spam and fraudulent reviews was investigated. Additionally, In the
work of Yue et al. (2019) and Liu et al. (2012) conducted research on the effectiveness
of internet reviews. The Authors (Jain et al. 2021b) discuss machine learning applica-
tions that incorporate online reviews in sentiment categorization, predictive decision-
making, and the detection of false reviews. In the work of Balaji et al. (2021) conducted
a thorough examination of the several applications of social media analysis utilizing
sophisticated machine learning algorithms. Authors present a brief overview of machine
learning algorithms used in social media analysis (Hangya and Farkas 2017).
The growth of social network sites has generated a slew of fields devoted to analyz-
ing these networks and their contents in order to extract necessary information. Sen-
timent analysis is concerned with deriving the sentiments communicated by a piece
of text from its content. Sentiment analysis is a subfield of NLP and that, given long
and illustrious public opinion for decision making, there must be multiple early works
addressing it. However, it still works going on sentiment analysis develop till the new
millennium.
Several real-world applications require sentiment analysis for detailed investigation.
for example, product analysis, discover which components or qualities of a product
appeal to customers in terms of product quality. In work of Subhashini et  al. (2021)
presents the results of a comprehensive review of contemporary opinion mining litera-
ture. It also covers how to extract text features from opinions with noise or uncertainty,
represent knowledge in opinions, and categorize them. Mowlaei et al. (2020) suggest a
technique for adaptive aspect-based lexicons for sentiment classification. The authors
described two strategies for constructing two dynamic lexicons to aid in the classifica-
tion of sentiments depending on their aspects: a strategy based on statistics and genetic
algorithms. A dynamic lexicon can be automatically updated and provides more precise
grading for context-related concepts (Kumar and Uma 2021). To organize all the aspects
of the reviews they selected a number of lexicons from several dictionaries. Sentiment
analysis is previously being applied in various domains ranging from hotels to airlines
and healthcare to the stock market (Zvarevashe and Olugbara 2018). Sentiment analy-
sis has applied to hotel reviews to get a better understanding of customer’s likes and
dislikes. In comparison (Valencia et al. 2019), it is used to determine the trends of the
stock market and cryptocurrencies based on the market sentiment. The Authors (Ahmad
et al. 2019a) analyze tweets relating to various domains and analyze the sentiments of
the tweets. The health care domain is seeing a surge in sentiment analysis applications
in recent times, customer opinion analyses (Ruffer et  al. 2020; Park et  al. 2020; Cor-
tis and Davis 2021; Arora et al. 2021), customer satisfaction analyses are few applica-
tions in the healthcare sector (Baashar et  al. 2020; Miotto et  al. 2018). The business
sector has always utilized sentiment analysis for its improvement. Sentiment analysis

13
A survey on sentiment analysis methods, applications, and… 5733

for various applications like reputation management, market research, and competitor
analysis, product analysis, customer voice, etc.
Various issues are associated with sentiment analysis and natural language processing,
such as individuals informal writing style, sarcasm, irony, and language-specific challenges.
There are many words in different languages whose meaning and orientation change depend-
ing on the context and domain in which they are employed. Therefore, there are not many
tools and resources available for all the languages. Sarcasm and irony are two of the most criti-
cal challenges that have recently attracted the attention of researchers. There has been much
development in detecting sarcasm and irony in text. There are many challenges in sentiment
analysis. In this work  we will analyze the variuos challenges, methodologies, applications,
and algorithms that are employed in sentiment analysis. We present the task with comparative
data analysis shown in tables, flow charts, and graphs that are simple to comprehend. Various
description of abbreviation which use in our work shown in Table 1.
To our understanding, existing surveys frequently skip some of the sentiment analysis
techniques in favor of machine learning, transformer learning, and lexicon-based approaches.
Although this paper covered all the task as well, it varies from earlier research in that it cov-
ers the most frequently used techniques. Additionally, other surveys study sentiment analysis
from a particular task, various challenges, or concentrate on a specific issue, such as product
reviews. This study provides a comprehensive investigation of sentiment analysis by discuss-
ing this area from various perspectives since it encompasses numerous research components
connected to sentiment analysis, such as problems, applications, tools, and approaches. This
work is highly beneficial to scholars and beginners, as it allows them to access a wealth of
knowledge about this area in a single paper. The survey important contributions can be sum-
marized as follows

• Several literature have been analyzed in order to thoroughly define the sentiment analysis
process and to identify well-known technologies for performing this work.
• Analyses of available methodologies in order to determine which one is most appropriate
for a certain application.
• We classify and summarize frequently used sentiment analysis approaches to understand
better accessible techniques such as machine learning, lexicon-based analysis, and hybrid
analysis.
• Summarizing the benefits and challenges of sentiment analysis in order to keep up of cur-
rent trending research.
• Each method comparison with their advantage and disadvantage, suggesting selecting the
proper method sentiment analysis task.
  The literature survey paper is organized as Sect. 2, Level of Sentiment Analysis, Sect. 3,
contain the Data Collection, Feature Extraction, and Feature Selection Method, explaining
all the steps from data extraction to various task of Sentiment Analysis, Sect. 4 contain
General Methodology for Sentiment Analysis and its Summary, Sect. 5, Contain the Senti-
ment Analysis Application in Various Domain, Sect. 6, Contain the Challenges in Senti-
ment Analysis, In the final Sect. 7, We Conclude our research work.

13
 5734 M. Wankhade et al.

Fig. 1  Level of sentiment
analysis

2 Sentiment analysis levels

Sentiment analysis has been investigated on several levels: Document Level, Sentence
Level, Phrase Level, and Aspect Level. Sentiment analysis in each level such as document,
sentence and phrase, aspect level shown in Fig. 1.

2.1 Document level sentiment analysis

Document-level: Document level sentiment analysis is performed on a whole document,

and single polarity is given to the whole document. This type of sentiment analysis is not
used a lot. It can be used to classify chapters or pages of a book as positive, negative, or
neutral. At this level, both supervised and unsupervised learning approaches can be utilized
to classify the document (Bhatia et al. 2015). Cross-domain and cross-language sentiment
analysis are the two most significant issues in document-level sentiment analysis. (Saun-
ders 2021) Domain-specific sentiment analysis has been shown to achieve remarkable
accuracy while staying highly domain-sensitive. In these tasks, the feature vector is a set of
words that must be domain-specific and limited.

2.2 Sentence level sentiment analysis

Sentence level: In this level of analysis, each sentence is analyzed and finding with a corre-
sponding polarity. This is highly useful when a document has a wide range and mix of senti-
ments associated with it (Yang and Cardie 2014). This classification level is associated with
subjective classification (Rao et  al. 2018). Each sentence polarity will be determined inde-
pendently using the same methodologies as the document level but with greater training data
and processing resources. The polarity of each sentence may be aggregated to find the senti-
ment of the document or used individually. Occasionally, document-level sentiment analysis
is insufficient for specific uses (Behdenna et  al. 2018). In previous work  on sentence-level
analysis has been devoted to finding subjective sentences. However, more difficult tasks, such

13
A survey on sentiment analysis methods, applications, and… 5735

www.amazon.com

Hotel Reviews twitter API

www.tripadvisor.com Corpus Based

Restaurant Sentiment Analysis
Approaches
Reviews
Data Pre- Subjectivity Classification
www.yelp.com
Processing
Airline Opinion Spam Detection
Dictionary Based
Reviews
Approaches
www.facebook.com
Aspect Detection
Data
Stock News Visualization Polarity Classification
Machine
Kaggle
Learning Based
Approaches
Product
Reviews Online Survey

www.airlinequality.com

Approach Task
Data Selection Data Scraping Data Analysis

Fig. 2  General procedure of sentiment analysis

as working with conditional sentences or ambiguous statements (Ferrari and Esuli 2019). In
these circumstances, sentence-level sentiment analysis is critical.

2.3 Phrase level sentiment analysis

Phrase level: Sentiment analysis also be performed where opinion words are mined at phrase
level, and classification will be done. Each phrase may contain multiple aspects or single
aspects. This may be useful product reviews of multiple lines; here, it is observed that a sin-
gle aspect is expressed in a phrase (Thet et al. 2010). It has been a hot topic of researchers
in recent times. While document-level analysis concentrated on categorizing the entire docu-
ment as subjective, either positively or negatively, sentence-level analysis is more beneficial,
as a document contains both positive and negative statements. Word is the most basic unit of
language; its polarity is intimately related to the subjectivity of the sentence or document in
which it appears. A sentence containing an adjective has a high probability of being a subjec-
tive sentence. (Fredriksen-Goldsen and Kim 2017) Additionally, the term chosen for expres-
sion represents the demographic characteristics of individuals, such as gender and age, and its
desire, social standing, and personality, other psychological and social characteristics (Flek
2020). As a result, term serves as the foundation for text sentiment analysis.

2.4 Aspect level sentiment analysis

Aspect level:  sentiment analysis is performed at the aspect level. Each sentence may con-
tain multiple aspects; therefore, Aspect level sentiment analysis. Primary attention to all the
aspects used in the sentence and assigns polarity to all the aspects after which an aggregate
sentiment has calculated for the whole sentence (Schouten and Frasincar 2015; Lu et al. 2011).

13
 5736 M. Wankhade et al.

Table 1  Various description of abbreviation

Abbreviation Description of abbreviation

NLP Natural Language Processing

NB Naïve Bayes
SVM Support Vector Machine
RF Random Forest
LR Logistic Regression
DT Decision Tree
LSTM Long Short-Term Memory
Bi-LSTM Bi-directional Long Short-Term Memory
CNN Convolutional Neural Network
RNTN Recursive Neural Tensor Network
RNN Recurrent Neural Network
ANN Artificial Neural Network
RNTN Recursive Neural Tensor Network
AI Artificial Intelligence
KNN K nearest Neighbours
LDA Latent Dirichlet allocation
ME Maximum Entropy
LSA Latent Semantic Analysis
CBOW Continuous Bag of words
SG Skip Gram
TF-IDF Term Frequency-Inverse Document Frequency
DNN Deep Neural Network
BoW Bag of Words
ABSA Aspect Based Sentiment Analysis
PoS Parts-of-Speech
NLTK Natural Language tool kit
DCNN Dynamic Convolutional Neural Network
BERT Bidirectional Encoder Representations from Transformers
MSA Multimodal Sentiment Analysis
GPT Generative Pre-trained Transformer
SLC Sentence Level Classification
AR-NN Auto-regressive Neural Network
DMN Dynamic Memory Networks
ELMo Embedding Language Models

3 Data collection and feature selection

3.1 Data collections

Data can be collected from the internet via web scraping, social media, news channels,
E-commerce websites, Forums, Weblog, some other websites shown in Fig. 2. Data Col-
lection is the first stage in the Sentiment Analysis. Depending on task sentiment analysis

13
A survey on sentiment analysis methods, applications, and… 5737

of findings, text data can be combined with other types of data like video, audio, loca-
tion, etc. A few essential sources of data collection are:
Social media: Social data refers to information gathered via social media networks. It
demonstrates how consumers interact with the product by accessing, posting, and exchang-
ing over. Academic study on individual, group and behavior uses social media as a dynamic
data source. It refers to Internet apps that are web or mobile-based that enable users to cre-
ate, access, and trade user-generated content.
Forums: Users can use message boards to discuss various topics, exchange opinions
and ideas, and solicit assistance via text messages. Forums are an intriguing source for
sentiment analysis due to the dynamic nature of user-generated information. Additionally,
researchers can undertake sentiment analysis on a specific domain by leveraging forums as
a source (Korkontzelos et al. 2016).
Weblog: A short weblog consists of paragraphs conveying a viewpoint, facts, personal
diary entries, or links. Together referred to as posts, that are chronologically sorted with
the most recent entry appearing first, in the style of a research article (Kumar and Teeja
2012). Blogs an valuable resource for performing sentiment analysis on a variety of entities
(Annett and Kondrak 2008).
Electronic Commerce website: Electronic Commerce websites where users can give
evaluations and express their opinions about a particular business or organization. In this
instance, websites that do not specifically review sites have millions of reviews, such as
e-commerce sites that feature product reviews1 or professional review sites such as.2 In
the work of Jain et al. (2019) conducted a descriptive study of the various airline service
classifications.

3.2 Feature selection

It is important to remember that developing a classification model requires first identifying

relevant features in dataset (Ritter et al. 2012). Thus, a review can be decoded into words
during model training and appended to the feature vector. For single word is considered,
the technique is called a “Uni-gram”; when two words are considered, the technique is
called a “Bi-gram”; and if three words are considered, the technique is referred to as a
“Tri-gram.” combination of unigram and bigram helpful for analysis (Razon and Barnden
2015); the context feature which helpful for getting results most accurate.
Pragmatic features are those that emphasize the application of words rather than a
methodological foundation. Pragmatics is the study of how context relates to perception in
linguistics and related sciences. Pragmatics is the study of phenomena such as implicature,
speech acts, relevance, and conversations.
Emoji are facial expressions used in sentiment analysis to convey emotions. Various
emoticons are used to depict a wide variety of human emotions (Tian et al. 2017). Emoti-
cons aid in conveying a person’s tone when composing a sentence and so aid in sentiment
analysis. Substitute their meaning for the emoticons: Review contain a range of emotions,
including happiness, sadness, and rage. Emoticons are classified into two categories: posi-
tive and negative sentiment emotions. Positive emotions are formed of positive emotions

1
  www.​amazon.​com.
2
  www.​yello​wpages.​com.

13
 5738 M. Wankhade et al.

such as love, happiness, and joy, while negative emoticons are composed of negative emo-
tions such as sadness, depression, and wrath.
Punctuation marks, or exclamation marks, serve to highlight the force of a positive or
negative remark. Similarly, the apostrophe and the question mark are other punctuation
marks.
Words in slang, such as lol and rofl. These are frequently used to introduce a sense of
humor into a remark. Given the nature of opinion tweets, it is plausible to assume that a
slang expression in the text suggests sentiment analysis. Substitute their meaning for the
slang term.
Punctuation marks, like exclamation marks, serve to highlight the force of a positive
or negative remark. Similarly, the apostrophe and the question mark are other punctuation
marks.

3.3 Feature extraction

Feature extraction is a key task in sentiment classification as it involves the extraction of

valuable information from the text data, and it will directly impact the performance of the
model. The approach tries to extract valuable information that encapsulates the text’s most
essential features. In the work of Venugopalan and Gupta (2015) incorporated other fea-
tures as it is challenging to extract features from the text. In most cases, punctuations are
removed from the text after lowering it in the pre-processing stage, but they used them to
extract features and hashtags and emoticons commonly used techniques for feature extrac-
tions listed below.
Terms frequency It is one of the simplest ways to express features that are more fre-
quently used in various NLP applications, including Sentiment Analysis, for information
retrieval. It considers a single word, i.e., uni-gram or group of two-three words, which can
be in bi-gram and tri-gram, with their terms count representing features (Sharma et  al.
2013). Term’s presence gives the word a value of either 0 or 1. Term frequency is the
integer value, which is its count in the given document. TF-IDF can be used as a weighted
scheme for better results that will measure the importance of any token in the given
document.
Parts of Speech tagging The process of tagging a word in a text (corpus) based on its
definition and context is also known as grammatical tagging. Tokens are categorized as
nouns, verbs, pronouns, adverbs, adjectives, and prepositions. For instance, “This mobile
is amazing” may be tagged as follows: (Straka et al. 2016) This :determiner, mobile:noun,
is:verb, amazing:adjective. For sentiment mining, an adjective is used more often as it rep-
resents the sentiment of the opinion. PoS taggers may be used for this task which is availa-
ble in NLTK or Spacy. Researches most commonly use Stanford PoS-tagger (Weerasooriya
et al. 2016).
Negations These are the words that can change or reverse the polarity of the opinion and
shift the meaning of a sentence. Commonly used negation words include not, cannot, nei-
ther, never, nowhere, none, etc. Every word appearing in the sentence will not reverse the
polarity; therefore, removing all negation words from stop-words may increase the compu-
tational cost and decrease the model’s accuracy. Negation words must be handled with at
most care (George et al. 2013). Negation words such as not, neither, nor, and so on are crit-
ical for sentiment analysis since they can revert the polarity of a given phrase. For instance,
the line “This movie is good.” is a positive sentence, but “The movie is not good.” is a
negative sentence. Regrettably, some systems eliminate negation words because they are

13
A survey on sentiment analysis methods, applications, and… 5739

included in stop word lists or are implicitly omitted since they have a neutral sentiment
value in a lexicon and do not affect the absolute polarity. However, reversing the polarity
is not straight forward because negation words might occur in a sentence without affecting
the text’s emotion.
In some cases, neutral sentiment is also included, and neutral evaluations are frequently
ignored in many sentiment analysis tasks due to their vagueness and lack of information, In
the work of Valdivia et al. (2018) considered to empower neutrality by defining the bound-
ary between positive and negative evaluations to improve the model performance. They use
several sentiment analysis approaches to various corpora, extracting their sentiment and fil-
tering out neutral evaluations by consensus, i.e., taking various models based on weighted
aggregation. Finally, then they compared the performance of single and aggregated models
in categorization. Other contribution introduced in the work of Wang et al. (2020) opinion
analysis, namely multi-level fine-scaled sentiment detection with ambivalence handling.
The ambivalence handler is detailed, as are the strength-level tuning settings for analyz-
ing the strength and fine-scale of both positive and negative attitudes (Buder et al. 2021).
It is capable of delving deeper into the text to uncover multi-level fine-scaled sentiments
and distinct emotional types. In the work of Valdivia et  al. (2017) suggest the usage of
induced ordered weighted averaging operators based on the fuzzy majority for the aggre-
gating polarity from many sentiment analysis methods. Their contribution is to establish
neutrality for opinions guided by a fuzzy majority.
Bag of Words (BoW) BoW is one of the simplest approach for extracting text features.
BoW will describe the occurrence of words in a document. Bag represents the vocabulary
of words using which a vector is formed for each sentence. The main problem with this
model is that it does not consider the syntactic meaning of the text. For instance, consider
two sentences s1= “the food was good”, s2= “the service was bad”. The vocabulary is
created for two sentences where v= {’the’, ‘food’, ‘was’, ‘service’, ‘bad’, ‘good’} and the
length of the vector is 6 and is represented as v1= [ 1 1 1 0 0 1] and v2= [1 0 1 1 1 0]. BoW
approach performance evaluated using (TF-IDF) which performs better in most cases.

3.3.1 Word embedding

Word embeddings represent words in a vector space by clustering words with similar
meanings together. Each word is assigned to a vector, which is then learned in a manner
similar to neural networks. It learns and chooses a vector from a predetermined vocabulary.
The dimension of the words may be chosen by passing it as a hyperparameter. SG model
and the continuous CBOW model are two of the most well-known algorithms for word
embeddings. Both of these are shallow window approaches methods in which a short win-
dow of some size, such as four or six, is specified, and the current word is anticipated using
context words in CBOW, while context words are forecasted using the current word in the
SG model. Word embeddings are concerned with learning about words in the context of
their local usage, which is specified by a window of nearby terms.
Word2vec word2vec is a 2-layer neural network that is used for vectorizing the tokens.
It is one of the famous and widely used vectorizing techniques developed by Mikolov et al.
(2013). Word2vec mainly has two models CBOW and SG. The CBOW model predicts the
target word using context words, whereas the SG model predicts the target word using con-
text words. With a larger dataset, the SG model performs better.
Global Vectors (GloVe) Global Vectors for word representation have developed (Pen-
nington et al. 2014) by an unsupervised learning approach to generate word embeddings

13
 5740 M. Wankhade et al.

from a corpus word-to-word co-occurrence matrix. GloVe is a popularly used method as

it is straightforward and quick to train GloVe model because of its parallel implementation
capacity (Al Amrani et al. 2018).
Fast Text It is an open-source and free library developed by FAIR (Facebook AI
Research) mainly used for word classifications, vectorization, and creation of word embed-
dings. It uses a linear classifier to train the model, which is very fast in training the model
(Bojanowski et al. 2017). It supports a CBOW and SG model. Semantic similarities may be
found using this model.
ELMo ELMo is a deep contextualized text representation. ELMo contributes to over-
coming the limitations of conventional word embedding approaches such as LSA, TF-IDF
and n-grams models (Peng et al. 2019). ELMo generates embeddings to words based on
the contexts in which they are used to record the word meaning and retrieve additional
contextual information. Through pretraining, ELMo can more accurately represent polyse-
mous words in a variety of contexts and is more informative about the text’s higher-level
semantics (Ling et al. 2020).

3.4 Feature selection approach

Feature Selection Approach is evaluated to identify a data characteristic. A characteris-

tic can be insignificant, significant, or redundant. Various feature selection approaches are
used to eliminate irrelevant and superfluous characteristics (Ahmad et al. 2019b; Lata et al.
2020). Feature Selection is a procedure that identifies and eliminates superfluous and irrel-
evant characteristics from the feature list and thus increases sentiment classification accu-
racy. In  the work of  (Hailong et  al. 2014; Duric and Song 2012) sentiment analysis  for
feature selection include lexicon-based and statistical methods. Humans produce features
in lexicon-based techniques. Typically, the procedure begins with the collection of phrases
with a strong feeling to develop a limited feature set (Kolchyna et  al. 2015). The set is
augmented with additional terms via synonym detection or web resources (Ghazi et  al.
2015; Rizos et al. 2019). The benefit of these approaches is their efficacy, as they carefully
address aspects. Choosing handcrafted features is a lengthy and complicated process.
SentiWordNet is a sentiment lexicon built from the WordNet database, with each term
accompanied by numerical values indicating positive and negative sentiment. A well-
known example is a SentiWordNet lexicon. contrarily, statistical processes are entirely
automated and are widely used for feature selection, although they typically fail to distin-
guish between sentimental and non-sentimental features (Poria et  al. 2014; Varelas et  al.
2005). The authors (Cambria et al. 2020) proposed SenticNet as a way to include logical
reasoning into deep learning models for sentiment analysis.
Statistical techniques for feature selection are typically categorized into four categories:
filter, embedding, wrapper, and hybrid.
Filter approach This is the most often used technique of selecting features. It selects
features without utilizing any machine learning technique based on the general properties
of the training data. The feature is ranked using several statistical metrics, and then the
features with the highest rankings are chosen (Adomavicius and Kwon 2011).  They are
computationally inexpensive and well-suited for datasets with a high number of attributes.
The words “Information Gain”, “Chi-square”, “Document Frequency”, and “Mutual infor-
mation” are all used to refer to fundamental filter algorithms.
Wrapper approach This approach is based on machine learning algorithms since it
relies on the output of the machine learning algorithm. Approaches are often iterative and

13
A survey on sentiment analysis methods, applications, and… 5741

Fig. 3  Task of sentiment analysis

computationally demanding due to this dependency, but they can determine the optimal
feature set for that particular modeling algorithm. Wrapper techniques include creating fea-
ture subsets (forward or backward selection) plus various learning algorithms(such as NB
or SVM).
Embedded approach This method combines the feature selection procedure into the exe-
cution of the modeling algorithm. It employs classification methods that have a built-in fea-
ture selection capability (Imani et al. 2013). As a result, it is more computationally efficient
than the wrapper approach. However, this technique is algorithm-specific (Das et al. 2020).
Embedded techniques are frequently based on a variety of decision tree algorithms, includ-
ing CART (Kosamkar and Chaudhari 2013), C4.5, and ID3 (Quinlan 2014; Mezquita et al.
2020), and additional algorithms like LASSO (Hssina et al. 2014).
Hybrid approach This strategy combines filter and wrapper approaches; hybrid meth-
ods generally utilize multiple approaches to produce the optimum feature subset. Hybrid
techniques typically achieve excellent performance and accuracy through the use of many
approaches. Numerous hybrid feature selection algorithms for sentiment analysis have been
developed (Chiew et al. 2019).

3.5 Task of sentiment analysis

Overview of the various task of sentiment analysis as shown in Fig.  3 and explain as
follows.
Subjectivity classification This is frequently assumed to be the first stage in senti-
ment analysis. Subjectivity classification recognizes subjective hints, emotional phrases,
and subjective ideas. Tokens like ’hard’, ’amazing’ and ’cheap’ are identified (Kasmuri
and Basiron 2017). These indications are used to distinguish objective or subjective text
objects. In work of Kasmuri and Basiron (2017) involves determining whether or not there
is a particular subject in the given text. Subjectivity classification aims to keep undesirable
objective data items out of subsequent processing (Kamal 2013).
Sentiment classification Sentiment categorization is a well-known researched task in
sentiment analysis. Polarity determination is one of the subtasks of sentiment classification,

13
 5742 M. Wankhade et al.

and the term “Opinion analysis” is frequently used while referring to Sentiment Analysis.
It is a little duty aimed on determining the sentiment of each piece of text. Polarity is tra-
ditionally either positive or negative (Wang et al. 2014). In the work of Xia et al. (2015),
the opinion-level context is investigated, with intra-opinion and inter-opinion aspects being
finely characterized. Neutral is also included in some cases. With a trained classifier, the
cross-domain analysis predicts the sentiment of a target domain. Extracting the domain
invariant features and where they are distributed is a commonly used approach (Peng et al.
2018). The cross-language analysis is done similarly by training the model on a dataset
from a source language and then evaluating it on a dataset from a different language with
limited data. The ambiguity of word polarity is one of the obstacles that sentiment analysis
must overcome. In the work of Vechtomova (2017) and Singh et al. (2021b) demonstrated
that retrieval-based models provide an alternative to Machine Learning based strategies for
word polarity detection. Affective computing and sentiment analysis also have tremendous
potential as a subsystem technology for other systems (Cambria et al. 2017). They can aug-
ment the capabilities of customer relationship management and recommendation systems
by enabling the discovery of which features customers particularly enjoy or the omission of
items that have received highly unfavourable feedback from the suggestions.
Opinion Spam Detection Spam Detection has become a significant challenge in senti-
ment analysis because of the rising interest in e-commerce and review platforms. Opinion
spams, often known as fraudulent or phone reviews, are well-written comments supporting
or criticizing a product for their benefit. Opinion spam detection seeks to identify three
distinct characteristics of a phone review: the review’s content, the review’s metadata, and
real-world product expertise (Crawford et al. 2015). Machine learning algorithms are fre-
quently used to assess review material in order to detect dishonesty. The star or point rat-
ings, IP address of the user, geolocation of user, and other information are few Metadata
used in detecting spam opinions. In many circumstances, though, it is inaccessible for anal-
ysis. Real-world experience and knowledge are included in a third way. For example, if a
product with bad ratings and reviews is being rated high for a period, that can be put under
suspect and analyzed for opinion spam detection.
Implicit Language Detection Sarcasm, irony, and humor are generally referred to as
Implicit Languages. These equivocal and ambiguous form is speech is an arduous task
to detect, even by humans sometimes. However, this implicit language is an essential
aspect of a sentence and can completely flip the meaning and polarity of the sentence. For
instance, consider the phrase ’Brilliant, I am fired’. The word Brilliant is very positive, but
it describes irony or sarcasm when combined with later parts, i.e., "I am fired" it makes the
phrase "I am fired" more negative. Investigating signs such as emoticons, laughter emo-
tions, and extensive punctuation mark utilization are more classic approaches for detecting
implicit language (Fang et al. 2020; Filatova 2012).
Aspect Extraction Aspect level sentiment analysis is mainly composed of three steps
aspect extraction, polarity classification, and aggregation. The process of aspect-based
sentiment analysis starts with the extraction of aspect, one of the key processes as this
differentiates usual sentiment analysis. Aspects can be extracted using a predefined set of
aspects which should be carefully predefined based on the domain on which it is used.
Other approaches are more sophisticated approaches like Frequency-based methods, syn-
tax-based methods, supervised and unsupervised machine learning approaches. It has been
seen that in reviews (Kanapala et al. 2019), few words are used more frequently than oth-
ers, and these most frequent terms are more likely to turn out as aspects; this straightfor-
ward method can turn out into quite a powerful approach by fact that a significant num-
ber of approaches. This approach has few shortcomings because all frequent nouns do

13
A survey on sentiment analysis methods, applications, and… 5743

Fig. 4  Approach of sentiment analysis

not refer to aspects, terms like ’bucks,’ ’dollars,’ ’rupees,’ etc. Also, aspects that are not
mentioned frequently can be missed by this method. A set of rules can be supplemented
with a frequency-based approach to overcome these problems, but these manually crafted
rules tend to come from parameters that need to be tuned manually, which is a hectic and
time-consuming task. Instead of focusing on the Frequency-based approach. Syntax-based
approach can be used as this approach covers the flaws of the frequency-based approach of
not detecting less frequent aspects (Bai et al. 2020). In this approach, For example, here,
’Awesome’ refers to an adjective referring to the aspect “food” in ’Awesome food.’ For this
approach, many annotated data covering all syntactical relations should be collected for
training the algorithm.

3.5.1 Need of sentiment analysis

Sentiment analysis is incredibly significant since it helps businesses understand their con-
sumers sentiment towards their brand. By automatically classifying the emotions behind
social media interactions, reviews, and more, organizations can make informed decisions.
Sentiment Analysis refers to the methods and strategies that enable firms to examine data
about how their customer base feels about a given service or product. To identify the Polar-
ity:? Indicates whether an emotion is good or negative.? Subject: What is the subject of dis-
cussion? Who is the holder of the opinion:? A thing or person that conveys the sentiment.
Sentiment Analysis is a process that analyzes natural language utterances automatically,
discovers essential claims or opinions, and classifies them according to their emotional
attitude.

• In the business needs with sentiment analysis has increased consumer happiness
through enhanced products, real-time problem detection, and market distinctiveness.
• Customer satisfaction analysis through sentiment analysis: The customer shares his
experience with a product and communicates his opinion and attitude about it using
natural language comments. This provides us with crucial insight into whether the con-
sumer is satisfied and, if necessary, how we can improve the product.

13
 5744 M. Wankhade et al.

• Identify and act in real-time problems: Through social media, a customer can immedi-
ately voice his discontent to the entire world.

4 Methodology

Three mainly used approaches for Sentiment Analysis include Lexicon Based Approach,
Machine Learning Approach, and Hybrid Approach. In addition, researchers are continu-
ously trying to figure out better ways to accomplish the task with better accuracy and lower
computational cost. Overview various methods used in Sentiment Analysis as shown in
Fig. 4. General Method about the Data collection, Feature selection and Sentiment analysis
task are shown in Fig. 2 which understand the overall scenario of sentiment analysis task
and overall method workflow.

4.1 Lexicon based approach

Lexicons are the collection of tokens where each token is assigned with a predefined score
which indicates the neutral, positive and negative nature of the text (Kiritchenko et  al.
2014). A score is assigned to tokens based on polarity such as + 1, 0, − 1 for positive,
neutral, negative or the score may be assigned based on the intensity of polarity and its val-
ues range from [+ 1, − 1] where + 1 represents highly positive, and − 1 represents highly
negative. In Lexicon Based Approach, for a given review or text, the aggregation of scores
of each token is performed, i.e., positive, negative, neutral scores are summed separately.
In the final stage, overall polarity is assigned to the text based on the highest value of indi-
vidual scores. Thus, the document is first divided into tokens of single words, where-after
the polarity of each token is calculated and aggregated in the end.
The lexicon-based technique is extremely feasible for sentiment analysis at the sentence
and feature level. Because no training data is required, it might be termed an unsupervised
technique. On the other side, the primary disadvantage of this technique is domain depend-
ence, as words can have several meanings and senses, and therefore a positive word in one
domain may be negative in another. For instance, given the word “small” and the sentences
“The TV screen is too small” and “This camera is extremely small”, the word “small” in
the first sentence is negative, as people generally prefer large screens, whereas in the sec-
ond sentence it is positive, as if the camera is small, it will be easy to carry. This issue can
be overcome by developing a domain-specific sentiment lexicon or by adapting an existing
vocabulary.
The advantage of the lexicon-based approach is that not require any training data and
is considered an unsupervised approach by some experts (Yan-Yan et al. 2010). The main
disadvantage with lexicon-based approach is that it is highly domain orientated and words
pertaining to one domain cannot be used in another domain (Moreo et  al. 2012). For
instance, consider the word huge it may be positive or negative based on the domain in
which it is being used. In “the queue for the movie was huge” the word may be considered
positive whereas, in “there was a huge lag in network” the word can be considered nega-
tive. Therefore, the polarity should be assigned to words carefully, considering the domain.
There are mainly two approaches used in Lexicon Based Approaches: Corpus Based and
Statistical Approach explain below, Comparative Analysis of Lexicon Based Classification
Method and its individual Advantage and Disadvantage are shown in Table 3.

13
A survey on sentiment analysis methods, applications, and… 5745

4.1.1 Corpus based approach

The approach employs semantic and syntactic patterns to ascertain the sentence’s emo-
tion. This approach begins with a predefined set of sentiment terms and their orientation
and then investigates syntactic or similar patterns to discover sentiment tokens and their
orientation in a huge corpus. This is a situation-specific method that requires a signifi-
cant amount of labeled data to train. However, it aids in resolving the issue of opinion
words with context-dependent orientations.
In the work of Park and Kim (2016) used a corpus based method for sentiment anal-
ysis. They used linguistic constraints and connectives to find the sentiment of a new
token. For instance, tokens on either side of correlative conjunctions like "AND" tend
to have the same orientation while words like "OR", but point out opinion change or the
tokens on opposite orientations. Although this idea is popularly known as Sentiment
Consistency, in practice, this is not that consistent. So, they constructed a graph that
contained tokens in vertices and their corresponding word in edges, after which a linear
log model was used to identify if two conjoined adjectives were or same or opposite ori-
entation and later clustered into a set of positive or negative words.
The corpus-based approach has the following types of approaches: Statistical
Approach and Semantic Approach as explained below.
Statistical Approach The seed opinion words or co-occurrence patterns can be found
using statistical approach. The rough idea behind this approach is that if it appears
in positive texts more than negative texts, then it is more likely to be positive or vice
versa. The key premise of this approach is that if comparable sentiment tokens are fre-
quently observed in the same environment, they will likely have the same orientation.
As a result, the orientation of the new token is determined by the frequency with which
it appears alongside other tokens detected in a similar context. In Turney and Littman
(2003) approach for calculating mutual information can be used to calculate the fre-
quency of co-occurrences of tokens.
A statistical approach is mostly used in several sentiment analysis applications. One
such application is detecting manipulated reviews by running a statistical test of ran-
domness popularly known as training test. In work of Hu et  al. (2012) expected that
reviews written by customers would have random writing styles due to the random back-
grounds of customers. They used a book review dataset from amazon.com to confirm
their results but, it was found that close to 10.3 percent of products were subjected to
online review manipulations.
LSA is another statistical technique for analyzing links between papers and tokens
referenced in the documents in order to generate essential patterns connecting to the
documents and phrases. In work of Cao et al. (2011) in used LSA to find semantic quali-
ties from reviews to investigate the effect of various features. They engaged program
user feedback dataset from the CNETdownload.com website. Their main objective was
to find out why few reviews received helpful votes while few reviews helpful votes.
They determined various factors which may affect the helpful voting pattern for reviews.
Semantic Approach In this approach, the similarity score is calculated between
tokens that are used for Sentiment Analysis. Wordnet is commonly used for this task.
Antonyms and synonyms can be easily found using this approach as similar words have
a positive score or higher value. In Maks and Vossen (2012) proposed that semantic
approach can be used in various applications to build a lexicon model that can be used
to describe adjectives, verbs, and nouns to use in Sentiment Analysis. They described,

13
 5746 M. Wankhade et al.

the in-depth description of subjectivity relations among the characters in a statement

conveying distinct attitudes for each character. subjectivity tagged with the knowledge
relating to both identity and orientation of attitude holder. In work of Bordes et  al.
(2014), Bhaskar et  al. (2015), Rao and Ravichandran (2009) worked on the WordNet
dataset in their work. They determined that the viewer’s subjectivity and the actor’s sub-
jectivity might be distinguished in some instances (Hershcovich and Donatelli 2021).

4.1.2 Dictionary based method

Dictionary based approach consists of a list of predefined set opinion words collected
manually (Chetviorkin and Loukachevitch 2012; Kaity and Balakrishnan 2020). The pri-
mary assumption behind this approach is that synonyms have the same polarity as the base
word, while antonyms have opposite polarity. Large corpora like thesaurus or wordnet are
looked upon for antonyms and synonyms, after which it is appended to a group or seed
list prepared earlier. In the first stage, initial set of words are collected manually with their
orientation. Later the list is expanded by looking at the antonyms and synonyms in the
available lexical resources (Singh et  al. 2017; Ho et  al. 2014). Then the words are itera-
tively added to the list, and list is expanded. Manual evaluation or correction may be done
in the last stage to ensure the quality of it. Stefano and Andrea created SentiWordNet three-
way in Baccianella et  al. (2010) with the help of automatic annotations of WordNet 3′ s
synsets. Another famous resource thesaurus was created based on online dictionaries. In
the work of Park and Kim (2016) suggested a rule-based strategy for labelling sentiment
sentences and words in contextual advertising using a dictionary-based approach. This
approach is feasible only for small dictionary size. Another disadvantage of all lexicon-
based approaches (Hajek et al. 2020), including the dictionary-based approach, is finding
opinion words specific for each domain as the polarity may vary. General Procedure step
in Lexicon Unsupervised learning category shown in Fig. 6. Summary Analysis of Lexicon
Based Classification Method and its Advantage and Disadvantage shown in Table  3 and
Summary Analysis of Clustering Method and its Advantage and Disadvantage shown in
Table 2.

• Lexicon Method Based tools Summary Analysis of Lexicon Based method tools and
available Dictionary as explain below
• Pre-define Dictionary Utilize a pre-defined list of positive and negative words to deter-
mine the polarity of texts based on the frequency with which each category is repre-
sented.3.
• SentiWordNet SentiWordNet assigns numerical sentiment scores to WordNet synsets
that are either positive or negative.4
• Bing Liu’s Sentiment Lexicon A dictionary has 4783 helpful positive and negative
words.5
• SentiStrength Unless modified by any additional classification rules, texts are catego-
rized according to the highest positive or negative score for any constituent word.6

3
  http://​www.​wjh.​harva​rd.​edu/​~inqui​rer/
4
  http://​senti​wordn​et.​isti.​cnr.​it.
5
  https://​www.​cs.​uic.​edu/​~liub/​FBS/​senti​ment-​analy​sis.​html.
6
  http://​senti​stren​gth.​wlv.​ac.​uk.

13
 Table 2  Advantages and disadvantages of sentiment analysis clustering approaches
Technique Advantage Disadvantage

K-means Due to the fact that these algorithms accomplish complexity in linear If there are any ambiguities, it is not accurate enough
time, they are well-suited for massive datasets
The algorithm is not required to know the class of a document in The issue with these techniques is that
advance. Does not require training they are sensitive to the starting center locations and make the assump-
The algorithm is not required to know the class of a document in tion that the number of clusters is known
advance These methods struggle with anomalies and noise, as well as a non-
Does not require training convex cluster
This means that it is devoid of human intervention
Memory requirements are minimal
A low cost, efficient, and extremely convenient approach for sentiment
A survey on sentiment analysis methods, applications, and…

analysis
Fuzzy c-means It always converges It is susceptible to initial assumptions and may terminate at local mini-
mum
Computation time is high
Agglomerative algorithm Do not depend on the number of clusters or the center gravity Hierarchical algorithms have a high degree of time complexity. Although
it has superior clustering properties, its high cost limits its use in large-
scale data applications
Divisive algorithm Do not rely on the number of clusters or the center Algorithms can never erase prior actions
Simple to implement and, in some situations, produces the best results No target reduction is achieved directly. At sometimes, it can be challeng-
ing to
Determine the correct number of clusters using the dendogram
5747

13
 5748 M. Wankhade et al.

Table 3  Summary analysis of Lexicon based classification method and its advantage and disadvantage
Technique Advantage Disadvantage

Dictionary based Trained data are not required Opinion terms with a specific
Give good outcomes for domains with fewer bands content orientation
Quick access to the vocabulary of word meanings Incapable of finding opinion terms
with a specified content oriented
domain that are not included in
the lexicon
Corpus based The capacity to identify expressions of opinion Due to the lexicon’s broad scope,
with a particular content orientation. When performance varies
domains are distinct, provides superior results The difficulties of providing
substantial texts while also being
able to cover all of the text terms
means that they cannot be used
individually

Manual
Review
Training

Manual
Algorithm Review

Manual
Raw Trained Review Production
Data Model Algorithm

Fig. 5  General procedure for sentiment analysis in supervised machine learning category

• Opinion Identification Opinion Finder recognizes subjective statements automatically

and highlights several characteristics of their subjectivity, such as the source (holder) of
the subjectivity and terms included in phrases indicating positive or negative views.7
• National Taiwan University Sentiment Dictionary contain 2812 Positive and 8276 neg-
atives words.8
• WordNet-Affect WordNet-Affect is a WordNet Domains extension that includes a subset
of synsets that are appropriate for representing affective notions associated with emo-
tional words.9
• Affective Norms for English Words Affective Norms for English Words is a collection
of normative emotional ratings for a large number of English words. This collection of
linguistic materials has been graded for enjoyment, arousal, and dominance in order to
establish a baseline for future research on sentiment and attentiveness.10

7
  http://​mpqa.​cs.​pitt.​edu/​opini​onfin​der.
8
  http://​acade​miasi​nican​lplab.​github.​io.
9
  http://​csea.​phhp.​ufl.​edu/​media/​anewm​essage.​html.
10
  http://​csea.​phhp.​ufl.​edu/​media/​anewm​essage.​html.

13
A survey on sentiment analysis methods, applications, and… 5749

Clusters Production

Manual
Review

Clustering Manual
Algorithm Review

Raw Manual
Review
Data

Fig. 6  General procedure for sentiment analysis in unsupervised machine learning category

• LingPipe can work on a wide range of activities, such as identifying topics, identifying
named entities, parsing and indexing documents, database text mining, word segmenta-
tion, sentiment analysis, and language identification.11
• Apache OpenNLP provides support for parsing sentence, tokenization, part-of-speech
tagging, segmentation, chunking, named entity extraction, language recognition, and
coreference resolution.12
• Lexicon Sentiment Dictionary A language used in politics.13

4.2 Machine learning approach

Machine Learning Algorithms can be used to categorize sentiments. Sentiment analysis is

the process of identifying and quantifying the sentiment of text or audio using natural lan-
guage processing, text analysis, computational linguistics, and other techniques. Data Col-
lection from Social Media and processing step for sentiment analysis in Supervised Learn-
ing category shown in Fig. 5 and Unsupervised learning category shown in Fig. 6. There
are two primary in Machine Learning approaches to sentiment analysis:

• Supervised machine learning

• Lexicon-based unsupervised learning

This task can be accomplished using both supervised and unsupervised learning methodol-
ogies. Unsupervised strategies for sentiment analysis by utilizing knowledge bases, ontolo-
gies, databases, and lexicons that include detailed knowledge that has been selected and

11
  http://​alias-i.​com/​lingp​ipe.
12
  http://​incub​ator.​apache.​org/​openn​lp.
13
  http://​www.​lexic​oder.​com.

13
 5750 M. Wankhade et al.

prepared specifically for sentiment analysis. Supervised learning methods are more com-
monly used due to their accurate results. These algorithms need to be trained on a training
set before it is applied to the actual data. Features may be extracted from text data.
The machine learning technique utilizes syntactic and/or linguistic factors to address
sentiment classification as a standard text classification issue utilizing syntactic and/or lin-
guistic factors. The categorization model associates the underlying record’s features with
one of the class labels. The model is then used to predict a class label for a given instance
of an unknown class. When an instance is assigned only one label, we have a difficult cat-
egorization challenge. When a probabilistic value of labels assigned to an instance, this is
referred to as the soft classification issue. Machine learning enables systems to acquire new
abilities without being explicitly programmed to do so. Sentiment analysis algorithms can
be trained to read beyond simple definitions to comprehend contextual information, sar-
casm, and misapplied words. Commonly used algorithms include:

4.2.1 Naive Bayes (NB)

NB technique is utilized for both categorization and training. NB is a Bayesian classifi-

cation approach based on the theorem of bayes. NB is a probabilistic classifier that uses
Bayes theorem to predict the probability of a given set of features as part of any particular
label. The conditional probability that event A occurs given the individual probabilities of
A and B and conditional probability of occurrence of event B. Here it is assumed that fea-
tures are not dependent. BoW model may be used for feature extraction. Generally, NB is
applied when the training data size is small. NB classified as positive 10% more accurately
than negative classification. This led to a decrease in average accuracy when it was taken.
In the work of Kang et al. (2012) solved this problem using an improved version of the NB
classifier. They tested this model on to restaurant review dataset. In work of Tripathy et al.
(2015) used machine learning for the classification of reviews. They proposed a NB model
along with a SVM model (Hajek et al. 2020; Bordes et al. 2014). They used a movie review
dataset for training and testing the models. Two thousand reviews were trained after pre-
processing and vectorization of the training dataset. Count Vectorizer and TF-IDF were
used before training the machine learning model. NB model proposed in Tripathy et  al.
(2015) gave an accuracy of 89.05 percent in a K-fold Cross-validation. The performance
was better when compared to other models using the probabilistic NB algorithm (Calders
and Verwer 2010).

4.2.2 Support vector machine (SVM)

SVM approach, which uses hyper-planes, is used to analyze data and define decision lim-
its in this technique. SVM are a type of non-probabilistic supervised learning technique
that is frequently used for classification tasks. SVM primary objective is to determine the
hyperplane that best separates the data into distinct classes. As a result, SVM seeks out
the hyperplane with the highest feasible margin. In work of Li and Li (2013) used Sup-
port Vector Machines for sentiment polarity Classifier. Classifying reviews based on their
quality is one of the many purposes for which SVM are utilized. Chen and Tseng (2011)
used two multiple class SVM based approaches. First being One-vs- all SVM and Multi-
class SVM to classify reviews. Second, a method was proposed to evaluate the quality of
the product review dataset quality by considering it as a classification problem. In work
of Dave et al. (2003) worked on MP3 reviews and digital camera reviews. Borg and Boldt

13
A survey on sentiment analysis methods, applications, and… 5751

(2020) used Linear SVM and VADER to predict customer reviews sentiment. The review
belonged to Huge Swedish Telecom Corporation. The dataset was huge and consisted of
168,  010 emails for training. They used Swedish sentiment Lexicon and VADER senti-
ment for initial labeling. Their (Li et al. 2019a) linear SVM model performed marvelously
with an F1 score of 83.4 percent and a mean AUC of 0.896. Furthermore, their model
highlighted a pattern that was predicted in Email conversations, using which sentiment of
unseen Email was being predicted. In work of Xia et al. (2020) urged that subjectivity of
opinion and credibility of expresser should be considered, unlike regular Binary Classifi-
cation Problem. A framework (Wu et  al. 2020) was proposed to summarize opinions on
microblogs. They found and retrieved the topics mentioned in the opinions related to users
inquiries and then categorized the opinions using SVM. Ali et al. (2020) also worked on
Twitter tweet data for the experiment. They found it to be beneficial to aggregate the opin-
ions for microblogs.

4.2.3 Logistic regression (LR)

A machine learning technique known as logistic regression works by multiplying an input

value by a weight value. It is a classifier that learns which input properties are most helpful
in identifying positive and negative classes. Logistic regression is a probabilistic regression
analysis used for classification tasks. For binary classification applications, logistic regres-
sion is commonly deployed. When there are multiple explanatory variables, logistic regres-
sion calculates the ratio of odds. Logistic regression uses Maximum-likelihood to calculate
best parameters. The independent variables may belong to any category i.e., Continuous,
Discrete (ordinal and nominal). LR model (Hamdan et al. 2015) that the dependent vari-
able is binary, and there is little or no multicollinearity between the predicting variables.

4.2.4 Decision tree (DT)

DT Classifier is a supervised learning technique where a tree is built using the training
example to classify the polarity of the text. DT uses a condition to divide data into parts
recursively. RF are used frequently than DT which combines multiple DT to avoid over-
fitting and improve accuracy. DT may be built using several algorithms like CART, ID3,
C5.0, C4.5 (Revathy and Lawrance 2017; Hssina et al. 2014; Singh and Gupta 2014; Patel
and Prajapati 2018). These are used the identify the best fitting attribute which needs to
be placed in the root (Gower 1966; Revathy and Lawrance 2017; Patil et al. 2012). Yan-
Yan et  al. (2010)using a graph-based strategy, They proposed a propagation strategy for
integrating sentence-level and sentence-level features. These two phrase characteristics are
referred to as inter and intra document verification. They tried to argue that determining
the sentiment classification of a review sentence entails more than simply examining the
statement’s components. They investigated the camera domain and compared their results
to those obtained using SVM and NB Classifiers. In the work of Jain et al. (2021a) tagged
data that can be used to distinguish between genuine and fraudulent reviews. Additionally,
we used two distinct datasets to test various machine learning techniques for categorization
(Yelp hotel review dataset, Yelp restaurant review dataset).

13
 5752 M. Wankhade et al.

4.2.5 Maximum entropy (ME)

Conditional Exponential Classifiers: Conditional exponential classifiers encode labelled

feature sets as vectors or arrays of integers. This vector is then used to compute feature
weights, which can be used to select the most likely label for the feature set. Entropy is a
measure of unpredictability. The Entropy is maximum for uniformly distributed data. The
input data consists of texts and ratings from 1-5 polarity assigned to it. Most popularly
used algorithms include SVM, NB, ME (Khairnar and Kinikar 2013; Kaufmann 2012)
used ME Classifier to detect parallel sentences in any two-language pair, which have less
training data. The other models used either required a massive amount of training data-
set or used a language-specific technique (Bergsma et  al. 2012), but their model showed
improved results could be produced using any pair of languages. This will enable the estab-
lishment of parallel corpora for various languages.

4.2.6 K‑nearest neighbours (KNN)

KNN algorithm is not extensively used in sentiment analysis but has shown to produce
good results when trained carefully. It operates on the fact that the classification of a test
sample will be similar to nearby neighbours. The K value may be selected on any hyper-
parameter tuning algorithms like Grid search or Randomized search cross validation. The
polarity may be hard voted based on K nearest neighbors values, or soft addition may be
done to find overall polarity.

4.2.7 Semi‑supervised learning

In this case, where the training dataset contains both labelled and unlabelled data, semi-
supervised learning appears to be a viable option (Zhu and Goldberg 2009). It is motivated
that while gathering unlabelled data is relatively easy in many real-world applications,
such as collecting articles from various blogs, labelling is expensive or labour-consuming
because labelling the training dataset is typically performed by humans. Ortigosa-Hernán-
dez et al. (2012) introduced in the work of a real-world situation in which the user attitude
is defined by three distinct (but related) target variables: subjectivity, sentiment solarity,
and will to influence. In the work of Janjua et  al. (2021) framework for semi-supervised
machine learning that combines pre-processing and classification algorithms for unlabelled
datasets.
Summary of different Sentiment Analysis Techniques its Advantage and Disadvantage
shown in Table 5.

4.3 Hybrid approach

Hybrid approach combines machine learning and lexicon-based approaches. Hybrid is a

term that refers to the combination of machine learning and lexicon-based techniques to
sentiment analysis. The hybrid technique combines the two and is extremely popular, with
sentiment lexicons playing a significant role in the majority of systems. Sentiment analysis
is a hybrid approach, including both statistical and knowledge-based methods for polarity
recognition. In the work of Hassonah et  al. (2020a) proposed a hybrid machine learning
approach using SVM and two feature selection techniques using the multi-verse optimizer

13
 Table 4  Summary analysis of machine learning classification algorithm and its advantage and disadvantage
Technique Advantage Disadvantage

NB Easy to Implement Assumes that attributes are mutually independent

Less training data required Model can face Zero Frequency Problem
Requires less training time and data than other approaches Limited by class imbalance, as a probability value must be estimated for
each conceivable value
SVM Most popular algorithm for SA Fine tuning of model is very difficult and tedious
Gives good accuracy for large dataset Long training time for large datasets
DT Easy to construct Model is more prone to overfit
Less time for training Highly Domain oriented model will be constructed
Extensive dataset is not required for training
KNN Non-linear decision boundaries can built Higher prediction complexity for large dataset and dimensions
Data can be added constantly with time without explicit training Equal importance is given to all features
RF The model is robust and very stable The model is very complex
Model is significantly less likely to overfit Longer time for training the data
A survey on sentiment analysis methods, applications, and…

ME Works on a probabilistic model. Therefore, lots of training data is not required Model is domain-oriented and will not perform well for different dataset
LR Simplest models to implement and training Linear boundaries are constructed
No assumptions made about distributions of classes in feature space Accuracy is low for complex dataset
DNN In comparison to other DL models, this one is rather simple to implement Over-fitting problem
RNN Capture of sequential data, which is critical for sentiment text categorization Train more slowly than other models
Complicated and computationally costly
LSTM More efficient than RNN Very complex model
Can map out long term dependencies Training time is high
Bi-LSTM Can find out dependencies in both the directions Computationally very costly
Better results can be obtained as compare to other method Training is very slow
CNN High Accuracy, Fast Training Design and maintenance are time-consuming
Transformer Uses self-attention models for finding dependencies Less popular and less used
Focuses only on important part of the sentence Require huge data
5753

13
 5754

13
Table 5  Summary of different machine learning sentiment analysis techniques its advantage and disadvantage
Technique Advantage Disadvantage

Supervised learning Method With the ability to assess a wide range of topics, Effective- Designated training documents capability of revealing subjective
ness in identifying the issue of subjectivity it demands human work and linguistic knowledge
Labeled data required
Unsupervised learning Method It do not need much human effort Its capacity to do so is not yet fully established
Labeled data not required
Semi-supervised learning Method Productive results in the presence of ambiguity If the unlabelled samples are noisy, the classifier suffers difficulty
Domain-oriented Sentiment Analysis Lexicon- Include a two-tiered classification system that includes Neglect the variety and depth of human feelings, as well as more
based Dictionary-based both positive and negative opinions emotional categories, aspects, and granularities
Classify sentiment on a certain scale Depends on Techniques
Eliminating objective sentences from a document can help
improve sentiment analysis effectiveness
M. Wankhade et al.
A survey on sentiment analysis methods, applications, and… 5755

and Relief algorithms (Chang et al. 2020). Sentiment analysis task (Al Amrani et al. 2018)
proposed using machine learning-based hybrid approach including RF and SVM. They
have shown that the individual models of SVM and RF had an accuracy of 81.01 and
82.03 percent, respectively, whereas the hybrid model combining both the algorithms had
an accuracy of close to 84% in the product review dataset provided by amazon.com. Few
researchers have proposed a hybrid architecture involving both lexicon-based and auto-
mated learning techniques to enhance the results. This is still a hot topic for researchers,
and lots of research needs to be done.
In work of Hassonah et  al. (2020b) used Twitter data for training. As many as 6900
tweets were extracted for training using the Twitter API. The results showed that their
model outperforms most of the models while reducing the total number of features up to
96%. They also pointed out the capacities of Hybrid models and concluded that Hybrid
models could outperform all the models with proper architecture and precise selection of
hyperparameters (Chang et al. 2020). The Hybrid model outperformed both the model in
all other metrics and comparisons. They concluded that although their Hybrid model per-
forms better than individual models, there are still many research opportunities available to
improve the performance of the hybrid model by tweaking and training the model. There
are various Method Summary Analysis of Supervised Machine learning Classification
Algorithm and its Advantage and Disadvantage shown in Table 4.

4.4 Neural network

Neural Network- In work of Van  de Camp and Van  den Bosch (2012) presented the use
of Neural networks and SVM in supportive relationships. They used biographical texts to
confirm their results. They were successful in marking relations between two individuals
as neutral, positive, or negative. They concluded that a SVM and a single layer Neural
Network had shown improved results. In work of Moraes et al. (2013a) presented a com-
parative empirical analysis between SVM and ANN in document-level sentiment analysis.
The motive of this comparison is that SVM was widely being used as an algorithm for
opinion mining as it had shown its capacity of getting accuracy. ANN, even though with
good potential, did not have much attention. In Moraes et  al. (2013b) they discussed all
the aspects related to both ANN and SVM, including their requirements, their accuracies,
and other contexts in which each model can perform the best. They have also implemented
a consistent evaluation framework using well-known participants in supervised methods
for selecting features and weights in orthodox BoW models. According to Medhat et  al.
(2014), Ravi and Ravi (2015) ANN had the edge over SVM in most of the cases, except
very few cases where there was a data imbalance. They used product reviews of Books,
GPS, and camera from amazon.com and Movie reviews to come to this conclusion. They
also pointed out potential problems and drawbacks of each model. An important disadvan-
tage of each model is the computational cost taken in training by ANN and the computa-
tional cost of SVM model in run time.
The traditional RNN (Liu et al. 2016) were used for various NLP tasks as they used
the previous time step information to predict the current time step, which ensures the
usage of previous information and acts as memory as it remembers some information
about a sequence. The most significant achievement or advantage of RNN was that it
used previous information, thus remembering the previous information, which acted
as memory. The main disadvantage of a traditional RNN is that it suffers from van-
ishing and exploding gradient descent, which means it cannot remember long-term

13
 5756 M. Wankhade et al.

relationships in the sequence. In the case of Bi-LSTM (Plank et  al. 2016) uses the
previous time step information along with next time step information to predict the
current time step, as pass the sequence in both the ways forward as well as backward.
Deep learning has identified new avenues for emulating the peculiarly human poten-
tial, for example-based learning. While this method of bottom-up learning is success-
ful for picture classification and object recognition, it is ineffective for NLP (Cambria
et al. 2020). They blend top-down and bottom-up learning in their work using an array
of symbolic and subsymbolic AI tools and apply them to the intriguing challenge of
text polarity detection.
RNN (Donkers et  al. 2017) have proven to improve results when trained on suffi-
cient data and computations. Variants of RNN (Pham and Le-Hong 2017) like LSTM
(Bandara et  al. 2020), GRU (Cheng et  al. 2020), Bi-LSTM (Abid et  al. 2019; Cho
and Lee 2019) have been used extensively in Sentiment analysis and related NLP task
(Abid et al. 2019; Khan et al. 2016). Attention models are being introduced recently,
which gives models an edge over another model. Recent transfer learning techniques
using BERT (Devlin et  al. 2018) and GPT (Ethayarajh 2019) are gaining the atten-
tion of researchers as the model is already trained on a massive corpus for days on
high-end GPU and Super computers. Weights can be fine-tuned using the training
dataset to get accurate results. Deep learning-based techniques are becoming highly
popular due to their outstanding performance in recent times. In the work of Yadav and
Vishwakarma (2020) and Wadawadagi and Pagi (2020) gives a detailed assessment of
common deep learning techniques that are widely employed in sentiment analysis. To
detect the intensity of sentiments and emotions, a stacked-ensemble model based on
deep learning was developed (Akhtar et  al. 2020). To better capture both long-term
dependencies and local features, they employ GloVe word embedding, bidirectional
GRU, bidirectional LSTM, attention mechanism, and CNN. The authors (Basiri et al.
2021) suggested a model for sentiment analysis based on attention (CNN-RNN). In the
work of Alhumoud and Al Wazrah (2021) conduct a systematic review of the literature
to identify, categorize, and evaluate state-of-the-art works utilizing RNNs for Arabic
sentiment analysis.
In 2017, researchers at the Google Brain team, Google Research and University of
Toronto came up with the concept of Transformers in their paper (Vaswani et al. 2017)
“Attention is all you need,” which revolutionized the NLP applications. This model is
a stack of encoder-decoder models consisting of self-attention, multi-headed attention
layers, and normalizing and feed-forward layers. The input is word embeddings along
with the position vector, which specifies the position of the vector and the inputs can
be given parallelly, unlike other models which take serial or sequential inputs. In the
encoder part, Self attention is calculated for each token with the help of key-value and
query vector. This is done multiple times and stacked over each other, forming a multi-
headed attention layer passed to the feed-forward layer (Kitaev and Klein 2018). There
are six encoder and six decoder layers present in the model. The input to the decoder
from an encoder is the two vectors K and V. The decoder layer has three layers: the self
attention layer, then a normalization layer which is the same as the encoder layer sec-
ond one is the encoder-decoder attention. The output self-attention and the input from
encoder are used to produce an output vector followed a feed forward network along
with a linear and a SoftMax layer (Juraska and Walker 2021). There are few skip con-
nections or residuals present in both encoders and decoders for better results.
There are various methods for sentiment analysis using machine learning and deep
learning used by the author are shown in Table 6. we are using several terms in Table 6

13
 Table 6  Sentiment analysis by using deep learning and machine learning method
References Method Lang. Dataset Task Result

Qiu et al. (2010) Rule Based English automotvieforums.com SA Recall = 0.375

Bai (2011) Markov Model, SVM, NB English IMDb SC SVM = 76.68, NB = 75.05
Fan and Chang (2011) Chi-square, SVM English ebay.com, wikipedia.com, SA Chi (matching) Pos = 74.8 Neg
epinions.com = 57.6 Uni-gram Pos = 59.1
Neg = 67.4
Rui et al. (2013) NB, SVM, rule-based English convinceme.net SC
Moraes et al. (2013b) NB, ANN, SVM English amazon.com SC Precision:Recall NB =
0.98:0.65 ANN = 0.86:0.85
SVM = 0.83:0.85
Socher et al. (2013) RNTN and RNN English Sentiment treebank SC
Lakkaraju et al. (2014) Joint Multi aspect sentiment English Beer Review and camera SC Beer = 77.04, Camera = 81.02
model + RNTN review
Vateekul and Koomsubha LSTM and Dynamic CNN English twitter SLC LSTM-75.30, DCNN-75.35
(2016)
A survey on sentiment analysis methods, applications, and…

Poria et al. (2016) Temporal CNN,RNN English Spanish MOUD Youtube dataset Multi-modal SC AND EC CNN,RNN = 96.55
Zhao et al. (2017) CNN LSTM English amazon reviews on digital SLC CNN-87.7, LSTM-87.9
camera, phone and laptop
Dragoni and Petrucci (2017) RNN English Dranziera dataset SC Dranziera dataset = 0.81
Chen et al. (2017) Deep fusion CNN English VSO : Flickr Images MVSO- Multi-modal SC VSO = 84.7, MVSO-EN =
EN: the dataset includes 73.7
concepts related to emo-
tions expressed
Wu and Chi (2017) Quadratic LSTM-RNN English Stanford sentiment SLC SST-86.6(binary) SICK-87.28
treebank(SST) and SICK
dataset
Uysal and Murphey (2017) CNN,LSTM, CNN+LSTM English IMDb, Sentiment 140, Document level SC S140-71.5 Nine-77.1 IMDB-
Nine public sentiment 89.1 Amazon-85.4
reviews,amazon multi
domain datset
5757

13
 Table 6  (continued)
5758

References Method Lang. Dataset Task Result

13
Yuan et al. (2018) Bi-LSTM with attention English amazon multi-domain and Multi-domain SC amazon = 87.69, sanders =
mechanism sanders twitter sentiment 86.32
dataset
Zhang et al. (2018) Dynamic Memory Networks English semeval2014, semeval 2016 SC DMN = 0.84
Rao et al. (2018) LSTM English Yelp 2014, 2015, IMDb Document level SC Yelp2014-63.9 Yelp2015-63.8,
IMDb-44.3
Naseem et al. (2020) Deep Intelligent Contextual English Airline Dataset SA airline dataset = 0.95
Embedding
Basiri et al. (2021) Attention based Bidirectional Sentiment140, Airline, Kindle SA (ABCDM) Kindle dataset =
CNN-RNN Deep Model dataset, movie review 0.93, Airline = 0.92, movie
(ABCDM) review = 0.90, Sentiment140
= 0.81
M. Wankhade et al.
A survey on sentiment analysis methods, applications, and… 5759

as SA indicates Sentiment Analysis, SC indicates Sentiment Classification. Categori-

zation of an individual method as Supervised Learning Method, Unsupervised Learn-
ing Method, Semi-supervised Learning Method, Domain-oriented Sentiment Analysis
Lexicon-based and Dictionary-based with its advantage and disadvantage are shown in
Table 5.

4.5 Other approaches

4.5.1 Aspect based sentiment analysis (ABSA)

ASBA is  valuable and rapidly growing part of sentiment analysis that has gained promi-
nence in recent years. Three critical phases compose aspect-level sentiment analysis:
aspect detection, polarity or sentiment categorization, and aggregation. Aspect detection
is a critical stage in Aspect-based Sentiment analysis, as it is followed by sentiment cal-
culation. Aspects are mined either by using pre-defined implicit aspects or can be mined
explicitly (Rana and Cheah 2016). Machine learning techniques, along with NLP tech-
niques, are used to mine aspects out of a sentence. Aspect level sentiment analysis is most
popular among product reviews or hotel reviews, as this approach will help them identify
various aspects focused by the review writers and help them rectify aspects that have a
negative sentiment (Tran et al. 2019). This is useful to both consumers as well as produc-
ers. For instance, for a hotel review dataset, implicit aspects may be defined as A= taste,
service, value, miscellaneous. For instance, consider a review R= “the food was awesome,
but service was slow”, this review consists of two aspects which are food and service, i.e.,
A = taste, service and the corresponding sentiment words are awesome and slow i.e. S =
awesome, slow which be classified as P = positive, negative which when aggregated is
neutral. If we consider the sentiment scores based on their positiveness or negativeness, the
aggregated polarity may vary.
Aspect level sentiment analysis has many challenges as it to identify the individ-
ual aspect(implicit or explicit) and classify as per sense is challenging to mine aspects
(Tubishat et al. 2018), Therefore, complex algorithms like LSTM, Bi-LSTM or pre-trained
models like BERT, GPT-2 may be used to accomplish the task. The researchers avoid
vanilla RNN as it faces many problems like vanishing and exploding gradient descent. It
is seen that recently attention-based models are being used in aspect detection. The next
step after aspect detection is polarity assignment to those mined aspects. There are multiple
approaches to perform the task, Machine learning algorithms may be used to complete the
task, or a dictionary-based approach may be used. Assigning the polarity to the aspect an
aggregation score may be calculated to find the overall polarity of the sentence. Hard or
soft voting is used to determine the sentence’s overall sentiment. Consumer sentiment is
assessed concerning qualitative content, quantitative ratings, and cultural factors in order to
forecast consumer recommendation decisions (Jain et al. 2021c, d).

4.5.2 Transfer learning

Transfer learning is one of the advances techniques in AI, where a pre-trained model can
use its acquired knowledge to transfer to a new model. Transfer learning uses the simi-
larity of data, distribution, and task. The new model directly uses the previously learned
features without needing any explicit training data. Training data may be used to fine-tune

13
 5760 M. Wankhade et al.

the model to a new task. This technique can be used to transfer knowledge of one domain
to another domain. This methodology has grown as a transfer learning technique because it
can produce great accuracy and results while requiring significantly less training time than
training a new model from scratch (Celik et al. 2020). Transfer learning is frequently used
in sentiment analysis to classify sentiments from one field to another field. In Meng et al.
(2019) developed a multiple-layer CNN based transfer learning approach. They used the
weights and biases of a convolutional and pooling layer from a pre-trained model to model.
They used the features from pre-trained model and fine-tuned weights of Fully connected
layers. This approach can produce good results when large labeled data sets are absent and
similarities in the tasks accomplished by the models. In the work of Bartusiak et al. (2015),
applied Transfer Learning to propose the sentiment analysis challenge. They used this tech-
nique to evaluate the sentiment at the document level in the polish language. They used
N-gram and Bi-gram to encode complex words and phrases. They used two different data-
sets from two different domains to provide evidence that knowledge gained from the train-
ing model suing dataset of one domain can be used for a dataset of another domain. Senti-
ment Analysis by using Deep learning and Machine Learning Method as shown in Table 6.
In 2018, Google AI Language Researchers open-sourced a new model for NLP called
BERT. It has a breakthrough and has taken the industry of deep learning by storm due
to its performance. In the work of Han et al. (2021) Transformer network revolutionized
the area of NLP and replaced the usage of LSTM and Bi-LSTM. The main advantage is
that Transformers do not suffer from vanishing or exploding gradient problems as they do
not use recurrence at all, and also, they are faster and less expensive to train. BERT is
an extension of the Transformers model proposed (Vaswani et al. 2017) in the “Attention
is all you need” paper. BERT uses transformers, an attention mechanism that learns con-
textual relationships between words or sub-words in a given text. The input in this model
contains the word embeddings and position embeddings, unlike transformers, but also has
an extra vector representing the sentence it belongs to handle two or more sentences at
a time. BERT consists of encoders based transformers; the encoder part is similar to the
transformer encoder. BERT has two models BERT base with 12 encoders stacked with
110 million parameters and BERT large model with 24 encoders stacked with 330 mil-
lion parameters. BERT model trained in two stages pre-training and fine-tuning. This is the
model main advantage as the fine-tuning with the dataset can be done as per the task. Such
as sentiment analysis (Singh et al. 2021a), aspect detection (Li et al. 2019b), spam detec-
tion (Yaseen et al. 2021), Transformer models for text-based emotion detection (Acheam-
pong et al. 2021), impact of coronavirus(singh2021sentiment). A single sentence or a pair
of sentences can be represented as a successive array of tokens using the task-specific
BERT architecture (Gao et al. 2019). In the work of Sun et al. (2019) transform ABSA to
a sentence-pair classification problem, such as question answering and natural language
inference, by constructing an auxiliary sentence from the aspect. BERT pre-trained model
has been fine-tuned.

4.6 Multimodal sentiment analysis (MSA)

MSA adds a new level to standard text-based sentiment analysis by incorporating addi-
tional modalities such as audio and visual data. Several studies have attempted to discern
sentiment analysis in social multimedia using a variety of multimodal inputs, including vis-
ual, audio, and textual data (Soleymani et al. 2017). Social multimedia sites such as You-
Tube, video blogs (vlogs), or spoken evaluations contain expressions of sentiment, such as

13
A survey on sentiment analysis methods, applications, and… 5761

Fig. 7  Confusion matrix

Negative Positive
True Positive False Negative

ACTUAL
False Postive True Negative

Positive Negative

PREDICTED

a video portraying a person discussing a product or a movie. Typically, spoken transcripts

are examined separately from face and voice expressions, and the results of unimodal,
text-based sentiment analysis are combined in post to create a “MSA” system. It may be
bimodal, consisting of various combinations of two modalities, or trimodal, consisting of
three modalities (Stappen et al. 2020). The majority of MSA techniques focus on develop-
ing complex fusion processes, ranging from attention-based models to tensor-based fusion.
MSA is a rapidly expanding area of study. A key area of opportunity in this subject is
to enhance the mechanism of multimodal fusion. In the work of Majumder et  al. (2018)
and Poria et al. (2018b) feature fusion technique that is hierarchical in nature, merging the
two modalities first and subsequently all three modalities. MSA of human spoken language
has developed into a significant subject of research (Liu 2012; Poria et al. 2017). Unlike
traditional emotional learning tasks that require the use of single modalities (text, speech),
multimodal learning makes use of many sources of information, including language (text/
transcripts/ASR), audio/acoustic, and visual modalities.

5 Performance evaluation parameter

The majority of state-of-the-art sentiment analysis makes use of accuracy, F1 score, and
precision. Sentiment analysis using deep learning architectures: a review utilizes recall and
accuracy as performance metrics. These metrics are as follows:
True Positive(TP): The number of positive reviews that have been correctly classified.
True Negative(TN):The number of negative reviews correctly classified as negative.
False Positive(FP): Number of incorrectly classified positive review.
False Negative(FN): Number of incorrectly classified negative review.
Precision Precision is defined as the ratio of correctly classified positive samples to
the total number of samples predicted as positive. This metric can be used to indicate the
strength of the prediction. i.e., if a model has 100 percent precision, all the samples evalu-
ated as positive are confidently positive.
TP
Precision = (1)
TP + FP
Recall Recall is also known as sensitivity. It is defined as the ratio of actual posi-
tive instances out of a total number of positive instances present in the classification. It
measures the misclassifications done by the model. Precision and recall are inversely

13
 5762 M. Wankhade et al.

Market Research and

Product Analysis
Competitor Analysis

Business
Intelligence
Reputation Sentiments of
Managment Customer Reviews

Health Care SA APPLICATIONS Review Analysis

Experince Analysis Aspect Analysis

Stock Market

Stock Price
Trend Prediction
Prediction

Fig. 8  Applications of sentiment analysis

proportional to each other. Therefore it is impossible to increase both Precision and Recall
at the same time. A recall is used in cases where the capture of a class is dominant.
TP
Recall = (2)
TP + FN
F1 score F1 score is the harmonic mean of Recall and Precision. It is the most used met-
ric after Accuracy. It is used when we are unable to choose between Precision or Recall. F1
score manages the trade-off between recall and precision.
Accuracy This is the most commonly used metric in all the classification tasks. Accu-
racy defines how accurate the model is. It is the ratio of correct classification to total pre-
dictions done by the model. Accuracy is a good metric to use for sentiment classification
for a balanced dataset.
Specificity Specificity Is the opposite of sensitivity. It is not popularly used by research-
ers but is helpful in few domains. It Is the ratio of the total number of correctly classified
negative samples to negative classes actually present in the confusion matrix as shown in
Fig. 7.
Confusion matrix A confusion matrix is a table that is frequently used to evaluate a cat-
egorization model’s (or “classifier’s”) effectiveness on a set of training test data values are
known. While the confusion matrix Fig. 7. itself is rather straightforward to comprehend,
the associated language might be perplexing.
TF-IDF Term Frequency refer to as number of times term present in a document. TF
which counts the number of times a term word appears in the document Because each doc-
ument is varied in length, it is likely that a term will appear far more frequently in longer
documents than in shorter ones. As a result, the phrase frequency is frequently divided by
the document length.
(Number of times term t present in a document)
Term Frequency = (3)
(Total number of terms in the document)

13
A survey on sentiment analysis methods, applications, and… 5763

(Total Number of document)

Inverse Document Frequency (IDF) = (4)
(number of terms t in the document)

TF − IDF =(TF) ∗ (IDF) (5)

6 Applications of sentiment analysis

Sentiment analysis has many applications, ranging from analyzing customer opinion, ana-
lyzing patient mental health status based on posts done on social media. Furthermore,
technological advances such as Blockchain, IoT, Cloud Computing, and Big Data have
broadened the range of applications for Sentiment Analysis, allowing it to be used in prac-
tically any discipline. Few most frequently used application in sentiment analysis shown in
Fig. 8. A few significant domains and industries where Sentiment Analysis is applied are
described below:

6.1 Business analysis

Sentiment analysis in the field of business intelligence offers several benefits. Additionally,
firms can utilize sentiment analysis data to improve products, investigate client feedback
and develop an innovative marketing strategy. The most typical use of sentiment analy-
sis in the field of business intelligence is analyzing customers impressions of services or
products. These studies, however, are not limited to product producers; consumers may
use them to review items and make more informed decisions. Sentiment analysis in busi-
ness intelligence has various benefits. For example, Businesses can use the results of Senti-
ment Analysis to make product enhancements, examine consumer feedback, or develop a
new marketing plan (Han et al. 2019). Sentiment analysis is most frequently used in busi-
ness intelligence to examine customers perceptions of products or services. However, these
analyses are not limited to product producers; consumers may also use them to compare
items and make a more informed choice. For eight years, (Bose et al. 2020) service food
reviews on amazon.com. Emotion lexicon, which classifies them into eight different emo-
tions and two moods (positive and negative). They found that sentiment analysis may be
used to identify customer behaviours and hazards and increase customer satisfaction.

6.1.1 Product reviews

As the e-commerce business is burgeoning, so is the number of products sold and reviews
given from the customers. Sentiment analysis one them will help customers choose better
products (Paré 2003). Phrase level or aspect level (Schouten and Frasincar 2015) sentiment
analysis performed on product reviews. Sentiment analysis can determine what the cus-
tomer thinks about its latest product after launching or examining comments and reviews.
Keywords for a specific product feature (food, service, cleanliness) can be chosen, and a
sentiment analysis framework (Mackey et al. 2015) can be trained to identify and analyze
only the necessary information.

13
 5764 M. Wankhade et al.

6.1.2 Market research and competitor analysis

Market research is perhaps the most common sentiment analysis application, besides brand
image monitoring and consumer opinion investigation. The purpose of sentiment analysis
is to determine who is emerging among competitors and how marketing campaigns com-
pare. It can be utilized to acquire a complete picture of a brand’s and its competitors con-
sumer base from the ground up. Sentiment analysis may collect data from several platforms
Twitter, Facebook, blogs, deliver tangible results, and overcome difficulties in business
intelligence.

6.2 Healthcare and medical domain

This is one of the industries where sentiment analysis is being utilized in recent times.
Data can be collected from various sources like surveys, Twitter (Carvalho and Plastino
2021), blogs, news articles, reviews, etc. This data can then be analyzed for various
use cases, one of them being an evaluation of standards and analysis of new updates in
the medical field. Domain experts are researching actively to find more uses of senti-
ment analysis and other NLP applications (Ebadi et  al. 2021). This application helps
healthcare service providers collect and evaluate patient moods, epidemics, adverse
drug reactions, and diseases to improve healthcare services. In work of Jiménez-Zafra
et  al. (2019) pointed out the difficulties in applying sentiment analysis in health care
because of the specific and unique terminologies used in the domain. In work of Clark
et al. (2018) used Twitter tweets concerning patient’s experiences as an add-on to ana-
lyze public health. Over a year, they generated roughly five million breast cancer-related
tweets using Twitter’s Streaming API. After pre-processing, the tweets were classified
with a standard LR classifier and a CNN model. Positive treatment experiences, rally-
ing support, and expanding public awareness were all linked. In conclusion, applying
sentiment analysis to analyze patient-generated data on social media can help determine
patients’ needs and views.

6.2.1 Reputation management

The application of sentiment analysis in diverse markets is brand monitoring and repu-
tation management. Evaluating how customers view their brand, product, or service is
beneficial to fashion companies, marketing agencies, IT companies, hotel chains, media
channels, and other businesses. Sentiment analysis tool adds more variety and intelli-
gence to the brand’s and their products portrayal. It enables businesses to track how
their customers perceive their brands and highlight the precise data about their attitudes.
Look for trends and changes, and pay attention to influencers presentations. Altogether,
sentiment analysis can be utilized in automating the media surveillance system as well
as the alarm system that goes with it. Keep track of the brand’s discussions and ratings
on various social media platforms.

13
A survey on sentiment analysis methods, applications, and… 5765

6.3 Review analysis

Sentiment analysis is extensively used in the domain of Entertainment. Reviews of

movie, shows, and short films may be analyzed to determine the viewer’s response
(Kumar et  al. 2019). This not only helps viewers make a better choice but also helps
good contents gain popularity. Sentence level (Lin and He 2009) Sentiment Analysis
has commonly used in this domain to determine the overall sentiment of the reviews
given accurately. The travel industry has sought to improve client experiences by devel-
oping machine learning and online consumer recommendation systems based on intel-
ligent, data-driven decision-making techniques (Jain et al. 2021f) also discussed catego-
rizing consumer decisions as positive or negative based on online reviews provided by
the valuable consumer(Jain et al. 2021e).

6.3.1 Customer reviews

Sentimental analysis on reviews on hotels and restaurants can help customers choose
better and also help the owners improve. Aspect-based sentiment analysis done on
hotels and restaurants will help identify the aspect with the most positive reviews and
negative reviews, on which Hotels can work and make it better. (Sann and Lai 2020;
Al-Smadi et al. 2018) According to sentiment analysis, this is one of the most attractive
industries. Sentimental analysis on reviews on hotels and restaurants can help customers
choose better and also help the owners improve (Zhao et al. 2019). ABSA (Akhtar et al.
2017) done on hotels and restaurants will help identify the aspect with the most positive
reviews and negative reviews, on which hotels can work and make it better. The service
providers profit the most since they may extract the aspect that receives the most nega-
tive feedback and improve on it.

6.3.2 Aspect analysis

Aspect-based sentiment analysis can help businesses make the most use of the massive
amounts of data they create. The aspect-based method will enable companies to extract
the most important aspects of client feedback and service.

6.4 Stock market

One of the applications of sentiment analysis is stock price prediction. It can be done
by analyzing all the news about the stock market and predicting the stock price trends.
Data can be collected from various sources like Twitter, news articles, blogs, etc. Sen-
tence level sentiment analysis can be done on these texts, after which the overall polar-
ity of texts will be decided of news of a particular company. In work of Xing et  al.
(2018) used to determine whether the trend will be rising or decreasing. Positive news
tended to lead to an upward trend, whereas negative news tended to lead to a downward
trend. Bitcoin and other digital cryptocurrencies relate to a novel technology known as
Blockchain. Participants inside the blockchain network verify the digital transactions
using peer to peer consensus methods. However, investigations which apply Sentiment
Analysis towards the area of blockchain technology are still infrequent, and those that
do exist, such as work in Kraaijeveld and De  Smedt (2020), have employed sentiment

13
 5766 M. Wankhade et al.

Table 7  Study of various challenges in sentiment analysis as per structure of data

References Challenge Structure of review

Heerschop et al. (2011) Negation Semi structure data(adjective)

Lapponi et al. (2012) Negation + huge lexicon Semi Structured data
Remus (2013) Negation + bi polar words Semi structured data , sentences or
topic documents
Chunping et al. (2014) Domain decencies Unstructured data, Emotion reviews
Hu et al. (2014) Short abbreviations Unstructured data
Kiritchenko et al. (2014) Emotions unstructured data
Cao et al. (2015) Ambiguity Semi-structured data
Flekova et al. (2015) Bi-polar words Unstructured data
Kasmuri and Basiron (2017) Opinion Spam Detections Structured data
Shayaa et al. (2018) Incomplete information and Sparsity Unstructured data and Structured data
Salah et al. (2019) and Mite- Domain dependency Unstructured data
Baidal et al. (2018)
Oueslati et al. (2020) Language dependency Unstructured data
Zuo et al. (2020) Implicit language Unstructured data
Acheampong et al. (2020) Emotion detection unstructured data
Kumar and Garg (2020) Multi-source data fusion Unstructured data, Structured data
Parvin et al. (2021) Informal speech, and slangs Unstructured data
Mendon et al. (2021) Multiple class classifications Unstructured data, Structured data

analysis to anticipate the value of digital cryptocurrencies. In the work of Rognone et al.
(2020) investigated the influence of news sentiment on cryptocurrencies like bitcoin and
other standard currencies volatility, volume, and returns.

6.5 Voice of customers

Take all user feedback from the call centres, emails, surveys, chats, and web and com-
bine and assess it. Sentiment analysis will allow categorizing and organizing data in
order to detect trends and reoccurring issues and worries. Sentiment analysis may aid
in identifying an appropriate customer group and subsequent value proposition develop-
ment, both of which are essential components of a successful business operation. On the
other hand, to stay updated and maintain the product in demand, it must have the finger
on the pulse of its customers.

6.6 Social media monitoring

Sentiment analysis of social data will monitor client sentiment 24 hours a day, seven
days a week, in real-time when anything unpleasant starts to circulate, which can rap-
idly reply and bolster image when getting favourable mentions. That also obtains con-
sistent, reliable information on clients, which can track progress from season to season
for the decision-making process. Because individuals provide their comments without

13
A survey on sentiment analysis methods, applications, and… 5767

being asked, social media posts frequently present some of the most honest points of
view regarding products, services, and enterprises. They are obliged to express their
feelings to the rest of the world.

7 Challenges in sentiment analysis

Sentiment analysis comes with various challenges ranging from computational cost to
informal writing and the presence of variations in languages. We look at the sentiment
analysis challenges that occur more frequently with certain types of sentiment structure,
as shown in Table 7. Few significant challenges faced in sentiment analysis are:

7.1 Structured sentiments

Structured sentiments are found in formal sentiment reviews, they are more focused
on formal problems such as books or research. Because the authors are professionals,
they are capable of writing thoughts or observations concerning scientific or factual
concerns.

7.2 Semi‑structured sentiments

Semi-Structured Sentiments fall between structured and unstructured sentiments. These

require an awareness of numerous review-related concerns. This style, which is depend-
ent on benefits and drawbacks, is listed separately by the authors, and the pros and cons
sections are typically comprised of brief sentences (Birjali et  al. 2021; Hussein 2018;
Ebrahimi et al. 2017; Mohammad 2017).

7.3 Unstructured sentiment

Unstructured Sentiment is an informal and free-flowing writing type in which the writer
is not constrained by any rules (Mukherjee et al. 2013). The text may comprise multi-
ple sentences, each of which could potentially include both pros and cons. For exam-
ple, unstructured reviews offer more opinion information than their formal counterparts
(Levashina et al. 2014). A feature explicitly stated: If a feature occurs in a review sen-
tence’s segment/chunk, the feature is referred to as an explicit feature of the product.
For instance, in the segment, the image is marvelous. The image is an explicit feature. If
a feature f is not explicitly mentioned in the review section but is implied, it is referred
to as an implicit feature of the product (Liu et al. 2010; Elith et al. 2011). For instance,
in the section, it is extremely pricey, and expensive is a feature sign. In light of the criti-
cal nature of sentiment analysis, this study examines the relationship between respond-
ents perspective structures and sentiment analysis issues.

13
 5768 M. Wankhade et al.

7.4 Methodological challenges

The majority of sentiment analysis in the modern day is data-driven machine learning
models adapting a sentiment analysis algorithm developed for product evaluations to
evaluate microblog postings is an unanswered question. Additionally, how to deal with
ambiguous situations and irony are key difficulties in sentiment analysis. For instance,
a sarcastic remark about an object is intended to communicate a negative sentiment;
yet, conventional sentiment analysis algorithms frequently miss this meaning. Numer-
ous methods have been proposed (Castro et  al. 2019; Medhat et  al. 2014) for detect-
ing sarcasm in language. However, the problem is far from resolved, as comedy is very
culturally particular, and it is challenging for a machine to understand unique(and fre-
quently fairly detailed) cultural allusions. In the work of Poria et al. (2018a) suggest by
incorporating vocal and facial expressions into multimodal sentiment analysis; This can
improve its success rate in identifying sarcastic comments. Furthermore, individuals
express sentiment for social reasons unrelated to their fundamental dispositions. For
instance, a person may transmit positive or negative thoughts to adhere to a specific
topic A norm or express and define one’s identity. Finally, machine-based sentiment
analysis is confined to outward expressions of sentiment, and conclusive information
about an individual expressed ideas is lacking.
Sentiment analysis is applicable to different types of data, each of which presents par-
ticular challenges. Sentiment analysis of human to machine and human to human interac-
tions requires very similar datasets to those used for emotion recognition. As a result, it has
the same limitations in terms of size and unreliable ground truth. In the work of McDuff
et al. (2014) have illustrated how webcams may be used to collect a large number of emo-
tional reactions, including sentiment. While this degrades the audiovisual capture qual-
ity, it achieves a scale that is not conceivable in the laboratory. Additionally, there is the
issue of labeling confidential laboratory data, which prohibits those permitted to examine
the data from performing the time-consuming operation of labeling. As a result, they are
restricted in terms of the amount of data they can collect in the laboratory and our ability
to label huge volumes of data. There are several methods for assessing feelings, but word
embedding algorithms such as word2vec and GloVe turn words into meaningful vectors.
These methods, on the other hand, ignore the word’s sentiment information (Wankhade
et al. 2021).
Multimedia information on websites is the second source of multi-modal sentiment
data. Social media provides us with a wealth of data that helps us to scale. The issue is that
the data acquired vary in terms of quality and context, and the data is limited to specific
populations that are more prevalent on the internet. However, because the data is publicly
available, crowd sourcing may be utilized to categorize it easily. According to the available
data on MSA, people are more prone to communicate positive or negative ideas online,
resulting in a scarcity of neutral opinions represented in all MSA studies evaluated.
Sarcasm People tend to use sarcasm when they do not meet their expectations. It is very
tough for machines to pick up sarcasm as many factors affect sarcasm, such as tone, situ-
ation, background information, etc. Sarcasm is a satirical remark that may look like prais-
ing but in reality. Sarcasm is used by people to criticize. Sarcasm is a type of sentiment in
which people express implicit information, usually the polar opposite of the message con-
tent, in order to emotionally hurt someone or mock something. Sarcasm detection in text
mining is one of the most challenging tasks in NLP, but it has lately become an interesting

13
A survey on sentiment analysis methods, applications, and… 5769

research subject due to its usefulness in enhancing social media sentiment analysis (Eke
et al. 2020).
Informal style of writing Informal style of writing is the biggest challenge to all NLP
tasks, including sentiment analysis. People are very casual about writing reviews or texts;
they tend to use acronyms, emojis, shortcuts in their text which is very hard to pick up.
Acronyms can be handled if they are universal. There are a lot of regional acronyms14
which change and grow day by day.
Grammatical errors Grammatical errors are very common in informal texts and can be
handled, but only to some extent; spelling errors can also be corrected limited. It is very
difficult to burgeoning the spelling mistake of users uniquely every time. The accuracy of
sentiment analysis and NLP tasks may be improved if these errors can be handled and
corrected.
Computational cost To get better accuracy, we need to increase the training data size
and complicate the model, which will exponentially increase the computational cost of the
model for training; high-end GPU may be required to train a model with a huge corpus.
Models like SVM, NB are not computationally costly, but neural networks and attention
models have shown that they are computationally costly.
Availability of data As NLP and sentiment analysis is a recently boomed technology,
the Availability of data may also be a challenge in some cases. Although data is available
in Twitter for sentiment analysis, high-quality training data is challenging for supervised
learning algorithms. Training data for ABSA is challenging to find online therefore needs
to be prepared manually. The training data of one domain may not be applicable and valu-
able to other domains. For instance, a model trained on a hotel review dataset is not helpful
in predicting sentiments of a stock or mutual fund dataset and vice versa.
Adaptations of language Languages change as they move to different regions and
places; although the base language remains the same, many factors influence language,
such as language prominence, pronunciation, literacy rate, etc. For instance, consider Eng-
lish language, which is widely spoken worldwide, but it is seen that many English varieties
are spoken worldwide based on the regions like Indian, American, British, etc. Lots of
words are used differently depending upon the region there are used. For instance, consider
the word “thong” which means flip-flops or slippers in Australia but means undergarments
in the UK. Similarly, different spellings for the same word, such as “color” and “colour,”
mean the same but are spelled differently in different regions. This will create duplicates
and may affect the accuracy and computational cost of the model. Language barrier is the
hardest of the challenges to NLP. There are thousands of languages spoken worldwide,
although NLP techniques are hardly available to 5-10 languages, and resources are widely
available for English.
Phrases containing degree adverbs and intensifiers Adverbs such as slightly, barely, and
moderately are used to quantify the sentiments. For instance, consider review r1= “The
food is barely good” and r2= “the food is really good”. r1 is considered neutral or slightly
positive, whereas r2 is considered to be highly positive. The adverbs ’barely’ and ’really’
decide the extent of positiveness and the word ’good’. Similarly, intensifiers also quantify
the sentiment of the sentences. Intensifiers like very, too are used to increase the positive-
ness or negativeness of the token. For instance, “too good” is considered to be more posi-
tive than “good.” Intensifiers and degree adverbs impose a challenge on aggregating the

14
  https://​www.​dicti​onary.​com/e/​acron​yms.

13
 5770 M. Wankhade et al.

sentiment values and comparing two sentences of the same sentiment rather than differenti-
ating between two sentences of opposite polarity.
The theoretical challenges employ a variety of approaches to enhance performance
when answering the particular sentiment challenges (Hunter et al. 2012). The theoretical
kind makes extensive PoS tagging and lexicon-based approaches (Taboada et  al. 2011).
The second approach is the BoW technique (El-Din 2016). Finally, there is the ME
approach. However, the most frequently used technique is the N-gram technique, which is
based on phrases and expressions when it comes to technical sentiment challenges (Wilson
et al. 2009). As well as the method that is used the least is the lexicon-based approach.
Mixed Code Data Code-mixing is the employment of vocabulary and grammar from
different languages in same sentence (Pravalika et al. 2017; Poria et al. 2020). Code Mix-
ing is a linguistic phenomenon that can occur in a multilingual situation where speakers
speak multiple languages. This phenomenon is becoming increasingly common as com-
munication between groups of people who speak different languages grows. Code-Mixing:
A review of Facebook posts created by Hindi-English users revealed a high code-mixing
level in the posts. The problems in the Hindi-English code-mixed text were reported using
a PoS tag annotated corpus. (Vijay et  al. 2018) a system that can detect the language of
the words, normalize them to their standard forms, assign their PoS tag, and split them
into chunks to handle the problem of shallow parsing of Hindi-English code-mixed social
media content. It’s frequent in multilingual societies and presents considerable difficulty to
NLP tasks like sentiment analysis. The lack of a formal grammar for code-mixed phrases
makes it challenging to identify compositional semantics, which is critical for conducting
sentiment analysis using rule-based and machine learning-based techniques. Furthermore,
because mixing is up to the individual, there are no predetermined mixing guidelines,
which is one of the significant drawbacks (Chatterjere et al. 2020). As a result, in order to
conduct sentiment analysis on code-mixed data, new language models must be developed.
In work of Chatterjere et al. (2020) and Singh et al. (2018) language modeling challenge
for code-mixed Hinglish text was investigated. However, despite the fact that Code Mix-
ing is a significant concern, few research has addressed it as thoroughly as the study of Lal
et al. (2019) (English-Hindi) code-mixed data for sentiment analysis, the authors presented
a hybrid architecture.

8 Conclusion

This article discussed sentiment analysis and associated techniques. The primary objective
of this work is to investigate and complete classification methods with their advantage and
disadvantages in sentiment analysis. To begin, several levels of sentiment analysis were
discussed, followed by a quick overview of necessary procedures such as data collection
and feature selection. Next, methods  of sentiment categorization systems were classified
and compared in terms of their advantages and disadvantages. Due to their simplicity and
excellent accuracy, supervised machine learning methods are often the widely utilized
technique in this discipline. Classification using NB and SVM algorithms are commonly
used as benchmarks against which newly proposed approaches can be compared. Several of
the most common application areas are discussed then the survey examines the significance
and consequences of sentiment analysis challenges in sentiment evaluation. The compari-
son investigates the relationship between the structure of sentiment reviews and the dif-
ficulties associated with sentiment analysis. This comparison reveals domain dependence,

13
A survey on sentiment analysis methods, applications, and… 5771

which is essential for identifying sentiment issues. The future work will consist of continu-
ously expanding the comparison area with additional findings. The subsequent challenges
illustrate that sentiment analysis is still a relatively unexplored subject of study.

References
Abid F, Alam M, Yasir M, Li C (2019) Sentiment analysis through recurrent variants latterly on convolu-
tional neural network of twitter. Futur Gener Comput Syst 95:292–308
Acheampong FA, Wenyu C, Nunoo-Mensah H (2020) Text-based emotion detection: advances, challenges,
and opportunities. Eng Rep 2(7):e12189
Acheampong FA, Nunoo-Mensah H, Chen W (2021) Transformer models for text-based emotion detection:
a review of BERT-based approaches. Artif Intell Rev 54:5789–5829
Adomavicius G, Kwon Y (2011) Improving aggregate recommendation diversity using ranking-based tech-
niques. IEEE Trans Knowl Data Eng 24(5):896–911
Ahmad S, Asghar MZ, Alotaibi FM, Awan I (2019) Detection and classification of social media-based
extremist affiliations using sentiment analysis techniques. Hum Centric Comput Inf Sci 9(1):1–23
Ahmad SR, Bakar AA, Yaakub MR (2019) A review of feature selection techniques in sentiment analysis.
Intell Data Anal 23(1):159–189
Akhtar MS, Ekbal A, Cambria E (2020) How intense are you? predicting intensities of emotions and senti-
ments using stacked ensemble [application notes]. IEEE Comput Intell Mag 15(1):64–75
Akhtar N, Zubair N, Kumar A, Ahmad T (2017) Aspect based sentiment oriented summarization of hotel
reviews. Procedia Comput Sci 115:563–571
Al Amrani Y, Lazaar M, El Kadiri KE (2018) Random forest and support vector machine based hybrid
approach to sentiment analysis. Procedia Comput Sci 127:511–520
Al-Smadi M, Qawasmeh O, Al-Ayyoub M, Jararweh Y, Gupta B (2018) Deep recurrent neural network vs.
support vector machine for aspect-based sentiment analysis of Arabic hotels’ reviews. J Comput Sci
27:386–393
Alhumoud SO, Al Wazrah AA (2021) Arabic sentiment analysis using recurrent neural networks: a review.
Artif Intell Rev 55:707–748
Ali SM, Noorian Z, Bagheri E, Ding C, Al-Obeidat F (2020) Topic and sentiment aware microblog summa-
rization for twitter. J Intell Inf Syst 54(1):129–156
Annett M, Kondrak G (2008) A comparison of sentiment analysis techniques: Polarizing movie blogs. In:
Conference of the Canadian Society for Computational Studies of Intelligence. Springer, pp 25–35
Arora A, Chakraborty P, Bhatia M, Mittal P (2021) Role of emotion in excessive use of twitter during
COVID-19 imposed lockdown in India. J Technol Behav Sci 6(2):370–377
Baashar Y, Alhussian H, Patel A, Alkawsi G, Alzahrani AI, Alfarraj O, Hayder G (2020) Customer rela-
tionship management systems (CRMS) in the healthcare environment: a systematic literature review.
Comput Stand Interfaces 71:103442
Baccianella S, Esuli A, Sebastiani F (2010) Sentiwordnet 3.0: an enhanced lexical resource for sentiment
analysis and opinion mining. Lrec 2010:2200–2204
Bai X (2011) Predicting consumer sentiments from online text. Decis Support Syst 50(4):732–742
Bai X, Liu P, Zhang Y (2020) Investigating typed syntactic dependencies for targeted sentiment classifica-
tion using graph attention neural network. IEEE/ACM Trans Audio Speech Lang Process 29:503–514
Balaji T, Annavarapu CSR, Bablani A (2021) Machine learning algorithms for social media analysis: a sur-
vey. Comput Sci Rev 40:100395
Bandara K, Bergmeir C, Smyl S (2020) Forecasting across time series databases using recurrent neural net-
works on groups of similar series: a clustering approach. Expert Syst Appl 140:112896
Bartusiak R, Augustyniak L, Kajdanowicz T, Kazienko P (2015) Sentiment analysis for polish using transfer
learning approach. In: 2015 second european network intelligence conference. IEEE, pp 53–59
Basiri ME, Nemati S, Abdar M, Cambria E, Acharya UR (2021) ABCDM: an attention-based bidirectional
CNN-RNN deep model for sentiment analysis. Futur Gener Comput Syst 115:279–294
Behdenna S, Barigou F, Belalem G (2018) Document level sentiment analysis: a survey. EAI Endorsed
Trans Context-aware Syst Appl 4(13):e2
Bergsma S, McNamee P, Bagdouri M, Fink C, Wilson T (2012) Language identification for creating lan-
guage-specific twitter collections. In: Proceedings of the second workshop on language in social
media, pp 65–74

13
 5772 M. Wankhade et al.

Bhaskar J, Sruthi K, Nedungadi P (2015) Hybrid approach for emotion classification of audio conversation
based on text and speech mining. Procedia Comput Sci 46:635–643
Bhatia P, Ji Y, Eisenstein J (2015) Better document-level sentiment analysis from rst discourse parsing.
arXiv preprint arXiv:​15090​1599
Birjali M, Kasri M, Beni-Hssane A (2021) A comprehensive survey on sentiment analysis: approaches,
challenges and trends. Knowl-Based Syst 226:107134
Bojanowski P, Grave E, Joulin A, Mikolov T (2017) Enriching word vectors with subword information.
Trans Assoc Comput Linguist 5:135–146
Bordes A, Glorot X, Weston J, Bengio Y (2014) A semantic matching energy function for learning with
multi-relational data. Mach Learn 94(2):233–259
Borg A, Boldt M (2020) Using VADER sentiment and SVM for predicting customer response sentiment.
Expert Syst Appl 162:113746
Bose R, Dey RK, Roy S, Sarddar D (2020) Sentiment analysis on online product reviews. In: Information
and communication technology for sustainable development. Springer, pp 559–569
Buder J, Rabl L, Feiks M, Badermann M, Zurstiege G (2021) Does negatively toned language use on social
media lead to attitude polarization? Comput Hum Behav 116:106663
Calders T, Verwer S (2010) Three naive bayes approaches for discrimination-free classification. Data Min
Knowl Disc 21(2):277–292
Cambria E, Das D, Bandyopadhyay S, Feraco A (2017) Affective computing and sentiment analysis. In: A
practical guide to sentiment analysis. Springer, pp 1–10
Cambria E, Li Y, Xing FZ, Poria S, Kwok K (2020) Senticnet 6: ensemble application of symbolic and
subsymbolic ai for sentiment analysis. In: Proceedings of the 29th ACM international conference on
information & knowledge management, pp 105–114
Cao Q, Duan W, Gan Q (2011) Exploring determinants of voting for the “helpfulness’’ of online user
reviews: a text mining approach. Decis Support Syst 50(2):511–521
Cao Y, Zhang P, Xiong A (2015) Sentiment analysis based on expanded aspect and polarity-ambiguous
word lexicon. Int J Adv Comput Sci Appl 6(2):97–103
Carvalho J, Plastino A (2021) On the evaluation and combination of state-of-the-art features in twitter
sentiment analysis. Artif Intell Rev 54(3):1887–1936
Castro S, Hazarika D, Pérez-Rosas V, Zimmermann R, Mihalcea R, Poria S (2019) Towards multimodal
sarcasm detection (an _obviously_ perfect paper). arXiv preprint arXiv:​19060​1815
Celik Y, Talo M, Yildirim O, Karabatak M, Acharya UR (2020) Automated invasive ductal carci-
noma detection based using deep transfer learning with whole-slide images. Pattern Recogn Lett
133:232–239
Chang JR, Liang HY, Chen LS, Chang CW (2020) Novel feature selection approaches for improving the
performance of sentiment classification. J Ambient Intell Humaniz Comput pp 1–14
Chatterjere A, Guptha V, Chopra P, Das A (2020) Minority positive sampling for switching points-an
anecdote for the code-mixing language modeling. In: Proceedings of the 12th language resources
and evaluation conference, pp 6228–6236
Chen CC, Tseng YD (2011) Quality evaluation of product reviews using an information quality frame-
work. Decis Support Syst 50(4):755–768
Chen X, Wang Y, Liu Q (2017) Visual and textual sentiment analysis using deep fusion convolutional neural
networks. In: 2017 IEEE international conference on image processing (ICIP). IEEE, pp 1557–1561
Cheng Y, Yao L, Xiang G, Zhang G, Tang T, Zhong L (2020) Text sentiment orientation analysis
based on multi-channel CNN and bidirectional GRU with attention mechanism. IEEE Access
8:134964–134975
Chetviorkin I, Loukachevitch N (2012) Extraction of Russian sentiment lexicon for product meta-
domain. In: Proceedings of COLING 2012, pp 593–610
Chiew KL, Tan CL, Wong K, Yong KS, Tiong WK (2019) A new hybrid ensemble feature selection
framework for machine learning-based phishing detection system. Inf Sci 484:153–166
Cho H, Lee H (2019) Biomedical named entity recognition using deep neural networks with contextual
information. BMC Bioinform 20(1):1–11
Chunping O, Wen Z, Ying Y, Zhiming L, Xiaohua Y (2014) Topic sentiment analysis in Chinese news.
Int J Multimed Ubiquitous Eng 9(11):385–396
Clark EM, James T, Jones CA, Alapati A, Ukandu P, Danforth CM, Dodds PS (2018) A sentiment analy-
sis of breast cancer treatment experiences and healthcare perceptions across twitter. arXiv preprint
arXiv:​18050​9959
Cortis K, Davis B (2021) Over a decade of social opinion mining: a systematic review. Artif Intell Rev
54:4873–4965

13
A survey on sentiment analysis methods, applications, and… 5773

Crawford M, Khoshgoftaar TM, Prusa JD, Richter AN, Al Najada H (2015) Survey of review spam
detection using machine learning techniques. J Big Data 2(1):1–24
Das H, Naik B, Behera H (2020) A jaya algorithm based wrapper method for optimal feature selection in
supervised classification. J King Saud Univ Comput Inf Sci
Dave K, Lawrence S, Pennock DM (2003) Mining the peanut gallery: opinion extraction and semantic
classification of product reviews. In: Proceedings of the 12th international conference on World
Wide Web, pp 519–528
Devlin J, Chang MW, Lee K, Toutanova K (2018) Bert: pre-training of deep bidirectional transformers
for language understanding. arXiv preprint arXiv:​18100​4805
Donkers T, Loepp B, Ziegler J (2017) Sequential user-based recurrent neural network recommendations.
In: Proceedings of the eleventh ACM conference on recommender systems, pp 152–160
Dragoni M, Petrucci G (2017) A neural word embeddings approach for multi-domain sentiment analysis.
IEEE Trans Affect Comput 8(4):457–470
Duric A, Song F (2012) Feature selection for sentiment analysis based on content and syntax models.
Decis Support Syst 53(4):704–711
Ebadi A, Xi P, Tremblay S, Spencer B, Pall R, Wong A (2021) Understanding the temporal evolution
of covid-19 research through machine learning and natural language processing. Scientometrics
126(1):725–739
Ebrahimi M, Yazdavar AH, Sheth A (2017) Challenges of sentiment analysis for dynamic events. IEEE
Intell Syst 32(5):70–75
Eke CI, Norman AA, Shuib L, Nweke HF (2020) Sarcasm identification in textual data: systematic
review, research challenges and open directions. Artif Intell Rev 53(6):4215–4258
El-Din DM (2016) Enhancement bag-of-words model for solving the challenges of sentiment analysis.
Int J Adv Comput Sci Appl 7(1):244–252
Elith J, Phillips SJ, Hastie T, Dudík M, Chee YE, Yates CJ (2011) A statistical explanation of maxent for
ecologists. Divers Distrib 17(1):43–57
Ethayarajh K (2019) How contextual are contextualized word representations? Comparing the geometry of
BERT, ELMO, and GPT-2 embeddings. arXiv preprint arXiv:​19090​0512
Fan TK, Chang CH (2011) Blogger-centric contextual advertising. Expert Syst Appl 38(3):1777–1788
Fang Z, Zhang Q, Tang X, Wang A, Baron C (2020) An implicit opinion analysis model based on feature-
based implicit opinion patterns. Artif Intell Rev 53(6):4547–4574
Ferrari A, Esuli A (2019) An NLP approach for cross-domain ambiguity detection in requirements engi-
neering. Autom Softw Eng 26(3):559–598
Filatova E (2012) Irony and sarcasm: corpus generation and analysis using crowdsourcing. In: Lrec, Cit-
eseer, pp 392–398
Flek L (2020) Returning the N to NLP: towards contextually personalized classification models. In: Pro-
ceedings of the 58th annual meeting of the association for computational linguistics, pp 7828–7838
Flekova L, Preoţiuc-Pietro D, Ruppert E (2015) Analysing domain suitability of a sentiment lexicon by
identifying distributionally bipolar words. In: Proceedings of the 6th workshop on computational
approaches to subjectivity, sentiment and social media analysis, pp 77–84
Fredriksen-Goldsen KI, Kim HJ (2017) The science of conducting research with LGBT older adults-an
introduction to aging with pride: National health, aging, and sexuality/gender study (NHAS)
Gao Z, Feng A, Song X, Wu X (2019) Target-dependent sentiment classification with BERT. IEEE Access
7:154290–154299
George DR, Rovniak LS, Kraschnewski JL (2013) Dangers and opportunities for social media in medicine.
Clin Obstet Gynecol 56(3)
Ghazi D, Inkpen D, Szpakowicz S (2015) Detecting emotion stimuli in emotion-bearing sentences. In: Inter-
national conference on intelligent text processing and computational linguistics. Springer, pp 152–165
Gower JC (1966) Some distance properties of latent root and vector methods used in multivariate analysis.
Biometrika 53(3–4):325–338
Hailong Z, Wenyan G, Bo J (2014) Machine learning and lexicon based methods for sentiment classifica-
tion: a survey. In: 2014 11th web information system and application conference. IEEE, pp 262–265
Hajek P, Barushka A, Munk M (2020) Fake consumer review detection using deep neural networks integrat-
ing word embeddings and emotion mining. Neural Comput Appl 32(23):17259–17274
Hamdan H, Bellot P, Bechet F (2015) Lsislif: Crf and logistic regression for opinion target extraction and
sentiment polarity analysis. In: Proceedings of the 9th international workshop on semantic evaluation
(SemEval 2015), pp 753–758
Han K, Xiao A, Wu E, Guo J, Xu C, Wang Y (2021) Transformer in transformer. arXiv preprint arXiv:​
21030​0112

13
 5774 M. Wankhade et al.

Han T, Liu C, Yang W, Jiang D (2019) A novel adversarial learning framework in deep convolutional neural
network for intelligent diagnosis of mechanical faults. Knowl-Based Syst 165:474–487
Hangya V, Farkas R (2017) A comparative empirical study on social media sentiment analysis over various
genres and languages. Artif Intell Rev 47(4):485–505
Hassonah MA, Al-Sayyed R, Rodan A, Ala’M AZ, Aljarah I, Faris H (2020) An efficient hybrid filter and
evolutionary wrapper approach for sentiment analysis of various topics on twitter. Knowl-Based Syst
192:105353
Hassonah MA, Al-Sayyed R, Rodan A, Ala’M AZ, Aljarah I, Faris H (2020) An efficient hybrid filter and
evolutionary wrapper approach for sentiment analysis of various topics on twitter. Knowl-Based Syst
192:105353
Heerschop B, van Iterson P, Hogenboom A, Frasincar F, Kaymak U (2011) Accounting for negation in
sentiment analysis. In: 11th Dutch-Belgian information retrieval workshop (DIR 2011), Citeseer, pp
38–39
Hershcovich D, Donatelli L (2021) It’s the meaning that counts: the state of the art in NLP and semantics.
KI-Künstliche Intelligenz pp 1–16
Ho C, Murad MAA, Doraisamy S, Kadir RA (2014) Extracting lexical and phrasal paraphrases: a review of
the literature. Artif Intell Rev 42(4):851–894
Hssina B, Merbouha A, Ezzikouri H, Erritali M (2014) A comparative study of decision tree id3 and c4. 5.
Int J Adv Comput Sci Appl 4(2):13–19
Hu N, Bose I, Koh NS, Liu L (2012) Manipulation of online reviews: an analysis of ratings, readability, and
sentiments. Decis Support Syst 52(3):674–684
Hu X, Tang J, Gao H, Liu H (2014) Social spammer detection with sentiment information. In: 2014 IEEE
international conference on data mining. IEEE, pp 180–189
Hunter ST, Cushenbery L, Friedrich T (2012) Hiring an innovative workforce: a necessary yet uniquely
challenging endeavor. Hum Resour Manag Rev 22(4):303–322
Hussein DMEDM (2018) A survey on sentiment analysis challenges. J King Saud Univ Eng Sci
30(4):330–338
Imani MB, Keyvanpour MR, Azmi R (2013) A novel embedded feature selection method: a comparative
study in the application of text categorization. Appl Artif Intell 27(5):408–427
Jain PK, Pamula R, Ansari S, Sharma D, Maddala L (2019) Airline recommendation prediction using cus-
tomer generated feedback data. In: 2019 4th international conference on information systems and
computer networks (ISCON). IEEE, pp 376–379
Jain PK, Pamula R, Ansari S (2021) A supervised machine learning approach for the credibility assessment
of user-generated content. Wirel Pers Commun 118(4):2469–2485
Jain PK, Pamula R, Srivastava G (2021) A systematic literature review on machine learning applications for
consumer sentiment analysis using online reviews. Comput Sci Rev 41:100413
Jain PK, Pamula R, Yekun EA (2021c) A multi-label ensemble predicting model to service recommendation
from social media contents. J Supercomput 1–18
Jain PK, Quamer W, Pamula R, Saravanan V (2021d) Spsan: sparse self-attentive network-based aspect-
aware model for sentiment analysis. J Ambient Intell Humaniz Comput 1–18
Jain PK, Saravanan V, Pamula R (2021) A hybrid CNN-LSTM: a deep learning approach for consumer sen-
timent analysis using qualitative user-generated contents. Trans Asian Low-Resour Lang Inf Process
20(5):1–15
Jain PK, Yekun EA, Pamula R, Srivastava G (2021) Consumer recommendation prediction in online reviews
using cuckoo optimized machine learning models. Comput Electr Eng 95:107397
Janjua F, Masood A, Abbas H, Rashid I, Khan MMZM (2021) Textual analysis of traitor-based dataset
through semi supervised machine learning. Futur Gener Comput Syst 125:652–660
Jiménez-Zafra SM, Martín-Valdivia MT, Molina-González MD, Ureña-López LA (2019) How do we talk
about doctors and drugs? sentiment analysis in forums expressing opinions for medical domain. Artif
Intell Med 93:50–57
Juraska J, Walker M (2021) Attention is indeed all you need: semantically attention-guided decoding for
data-to-text nlg. arXiv preprint arXiv:​21090​7043
Kaity M, Balakrishnan V (2020) Sentiment lexicons and non-english languages: a survey. Knowl Inf Syst
1–36
Kamal A (2013) Subjectivity classification using machine learning techniques for mining feature-opinion
pairs from web opinion sources. arXiv preprint arXiv:​13126​962
Kanapala A, Pal S, Pamula R (2019) Text summarization from legal documents: a survey. Artif Intell Rev
51(3):371–402
Kang H, Yoo SJ, Han D (2012) Senti-lexicon and improved Naïve Bayes algorithms for sentiment analysis
of restaurant reviews. Expert Syst Appl 39(5):6000–6010

13
A survey on sentiment analysis methods, applications, and… 5775

Kasmuri E, Basiron H (2017) Subjectivity analysis in opinion mining—a systematic literature review. Int J
Adv Soft Comput Appl 9(3):133–159
Kaufmann M (2012) Jmaxalign: a maximum entropy parallel sentence alignment tool. In: Proceedings of
COLING 2012: demonstration papers, pp 277–288
Khairnar J, Kinikar M (2013) Machine learning algorithms for opinion mining and sentiment classification.
Int J Sci Res Publ 3(6):1–6
Khan MT, Durrani M, Ali A, Inayat I, Khalid S, Khan KH (2016) Sentiment analysis and the complex natu-
ral language. Complex Adapt Syst Model 4(1):1–19
Kiritchenko S, Zhu X, Mohammad SM (2014) Sentiment analysis of short informal texts. J Artif Intell Res
50:723–762
Kitaev N, Klein D (2018) Constituency parsing with a self-attentive encoder. arXiv preprint arXiv:​18050​
1052
Kolchyna O, Souza TT, Treleaven P, Aste T (2015) Twitter sentiment analysis: Lexicon method, machine
learning method and their combination. arXiv preprint arXiv:​15070​0955
Korkontzelos I, Nikfarjam A, Shardlow M, Sarker A, Ananiadou S, Gonzalez GH (2016) Analysis of the
effect of sentiment analysis on extracting adverse drug reactions from tweets and forum posts. J
Biomed Inform 62:148–158
Kosamkar V, Chaudhari SS (2013) Improved intrusion detection system using c4. 5 decision tree and sup-
port vector machine. PhD diss, Doctoral dissertation, Mumbai University
Kraaijeveld O, De Smedt J (2020) The predictive power of public twitter sentiment for forecasting crypto-
currency prices. J Int Finan Markets Inst Money 65:101188
Kumar A, Garg G (2020) Systematic literature review on context-based sentiment analysis in social multi-
media. Multimed Tools Appl 79(21):15349–15380
Kumar A, Teeja MS (2012) Sentiment analysis: a perspective on its past, present and future. Int J Intell Syst
Appl 4(10):1
Kumar KN, Uma V (2021) Intelligent sentinet-based lexicon for context-aware sentiment analysis: opti-
mized neural network for sentiment classification on social media. J Supercomput 77:12801–12825
Kumar S, Yadava M, Roy PP (2019) Fusion of EEG response and sentiment analysis of products review to
predict customer satisfaction. Inf Fusion 52:41–52
Lakkaraju H, Socher R, Manning C (2014) Aspect specific sentiment analysis using hierarchical deep learn-
ing. In: NIPS Workshop on deep learning and representation learning, pp 1–9
Lal YK, Kumar V, Dhar M, Shrivastava M, Koehn P (2019) De-mixing sentiment from code-mixed text.
In: Proceedings of the 57th annual meeting of the association for computational linguistics: student
research workshop, pp 371–377
Lapponi E, Read J, Øvrelid L (2012) Representing and resolving negation for sentiment analysis. In: 2012
IEEE 12th international conference on data mining workshops. IEEE, pp 687–692
Lata K, Singh P, Dutta K (2020) A comprehensive review on feature set used for anaphora resolution. Artif
Intell Rev 54:2917–3006
Levashina J, Hartwell CJ, Morgeson FP, Campion MA (2014) The structured employment interview: narra-
tive and quantitative review of the research literature. Pers Psychol 67(1):241–293
Li F, Wang W, Xu J, Yi J, Wang Q (2019) Comparative study on vulnerability assessment for urban buried
gas pipeline network based on SVM and ANN methods. Process Saf Environ Prot 122:23–32
Li X, Bing L, Zhang W, Lam W (2019b) Exploiting BERT for end-to-end aspect-based sentiment analysis.
arXiv preprint arXiv:​19100​0883
Li YM, Li TY (2013) Deriving market intelligence from microblogs. Decis Support Syst 55(1):206–217
Ligthart A, Catal C, Tekinerdogan B (2021) Systematic reviews in sentiment analysis: a tertiary study. Artif
Intell Rev 54:4997–5053
Lin C, He Y (2009) Joint sentiment/topic model for sentiment analysis. In: Proceedings of the 18th ACM
conference on information and knowledge management, pp 375–384
Ling M, Chen Q, Sun Q, Jia Y (2020) Hybrid neural network for Sina Weibo sentiment analysis. IEEE
Trans Comput Soc Syst 7(4):983–990
Liu B (2012) Sentiment analysis and opinion mining. Synth Lect Hum Lang Technol 5(1):1–167
Liu B, Zhang L (2012) A survey of opinion mining and sentiment analysis. In: Aggarwal C, Zhai C (eds)
Mining text data. Springer, Boston, pp 415–463
Liu B et al (2010) Sentiment analysis and subjectivity. Handb Nat Lang Process 2(2010):627–666
Liu P, Qiu X, Huang X (2016) Recurrent neural network for text classification with multi-task learning.
arXiv preprint arXiv:​16050​5101
Lu B, Ott M, Cardie C, Tsou BK (2011) Multi-aspect sentiment analysis with topic models. In: 2011 IEEE
11th international conference on data mining workshops. IEEE, pp 81–88

13
 5776 M. Wankhade et al.

Mackey TK, Miner A, Cuomo RE (2015) Exploring the e-cigarette e-commerce marketplace: identifying
internet e-cigarette marketing characteristics and regulatory gaps. Drug Alcohol Depend 156:97–103
Majumder N, Hazarika D, Gelbukh A, Cambria E, Poria S (2018) Multimodal sentiment analysis using hier-
archical fusion with context modeling. Knowl-Based Syst 161:124–133
Maks I, Vossen P (2012) A lexicon model for deep sentiment analysis and opinion mining applications.
Decis Support Syst 53(4):680–688
McDuff D, El Kaliouby R, Cohn JF, Picard RW (2014) Predicting ad liking and purchase intent: large-scale
analysis of facial responses to ads. IEEE Trans Affect Comput 6(3):223–235
Medhat W, Hassan A, Korashy H (2014) Sentiment analysis algorithms and applications: a survey. Ain
Shams Eng J 5(4):1093–1113
Mendon S, Dutta P, Behl A, Lessmann S (2021) A hybrid approach of machine learning and lexicons to sen-
timent analysis: enhanced insights from twitter data of natural disasters. Inf Syst Front 23:1145–1168
Meng J, Long Y, Yu Y, Zhao D, Liu S (2019) Cross-domain text sentiment analysis based on cnn_ft method.
Information 10(5):162
Mezquita Y, Alonso RS, Casado-Vara R, Prieto J, Corchado JM (2020) A review of k-nn algorithm based on
classical and quantum machine learning. In: International symposium on distributed computing and
artificial intelligence. Springer, pp 189–198
Mikolov T, Chen K, Corrado G, Dean J (2013) Efficient estimation of word representations in vector space.
arXiv preprint arXiv:​13013​781
Miotto R, Wang F, Wang S, Jiang X, Dudley JT (2018) Deep learning for healthcare: review, opportunities
and challenges. Brief Bioinform 19(6):1236–1246
Mite-Baidal K, Delgado-Vera C, Solís-Avilés E, Espinoza AH, Ortiz-Zambrano J, Varela-Tapia E (2018)
Sentiment analysis in education domain: a systematic literature review. In: International conference
on technologies and innovation. Springer, pp 285–297
Mohammad SM (2017) Challenges in sentiment analysis. In: A practical guide to sentiment analysis.
Springer, pp 61–83
Moraes R, Valiati JF, Neto WPG (2013) Document-level sentiment classification: an empirical comparison
between SVM and ANN. Expert Syst Appl 40(2):621–633
Moraes R, Valiati JF, Neto WPG (2013) Document-level sentiment classification: an empirical comparison
between SVM and ANN. Expert Syst Appl 40(2):621–633
Moreo A, Romero M, Castro J, Zurita JM (2012) Lexicon-based comments-oriented news sentiment ana-
lyzer system. Expert Syst Appl 39(10):9166–9180
Mowlaei ME, Abadeh MS, Keshavarz H (2020) Aspect-based sentiment analysis using adaptive aspect-
based lexicons. Expert Syst Appl 148:113234
Mukherjee A, Venkataraman V, Liu B, Glance N (2013) What yelp fake review filter might be doing? In:
Proceedings of the international AAAI conference on web and social media, vol 7
Naseem U, Razzak I, Musial K, Imran M (2020) Transformer based deep intelligent contextual embedding
for twitter sentiment analysis. Futur Gener Comput Syst 113:58–69
Ortigosa-Hernández J, Rodríguez JD, Alzate L, Lucania M, Inza I, Lozano JA (2012) Approaching senti-
ment analysis by using semi-supervised learning of multi-dimensional classifiers. Neurocomputing
92:98–115
Oueslati O, Cambria E, HajHmida MB, Ounelli H (2020) A review of sentiment analysis research in Arabic
language. Futur Gener Comput Syst 112:408–430
Paré DJ (2003) Does this site deliver? B2B e-commerce services for developing countries. Inf Soc
19(2):123–134
Park HW, Park S, Chong M (2020) Conversations and medical news frames on twitter: infodemiological
study on covid-19 in South Korea. J Med Internet Res 22(5):e18897
Park S, Kim Y (2016) Building thesaurus lexicon using dictionary-based approach for sentiment classifica-
tion. In: 2016 IEEE 14th international conference on software engineering research, management and
applications (SERA), pp 39–44, https://​doi.​org/​10.​1109/​SERA.​2016.​75161​26
Parvin SA, Sumathi M, Mohan C (2021) Challenges of sentiment analysis-a survey. In: 2021 5th Interna-
tional conference on trends in electronics and informatics (ICOEI). IEEE, pp 781–786
Patel HH, Prajapati P (2018) Study and analysis of decision tree based classification algorithms. Int J Com-
put Sci Eng 6(10):74–78
Patil N, Lathi R, Chitre V (2012) Customer card classification based on c5. 0 & cart algorithms. Int J Eng
Res Appl 2(4):164–167
Peng M, Zhang Q, Jiang Yg, Huang XJ (2018) Cross-domain sentiment classification with target domain
specific information. In: Proceedings of the 56th annual meeting of the association for computational
linguistics (Volume 1: Long Papers), pp 2505–2513

13
A survey on sentiment analysis methods, applications, and… 5777

Peng Y, Yan S, Lu Z (2019) Transfer learning in biomedical natural language processing: an evaluation of
BERT and ELMo on ten benchmarking datasets. arXiv preprint arXiv:​19060​5474
Pennington J, Socher R, Manning CD (2014) Glove: global vectors for word representation. In: Proceed-
ings of the 2014 conference on empirical methods in natural language processing (EMNLP), pp
1532–1543
Pham TH, Le-Hong P (2017) End-to-end recurrent neural network models for vietnamese named entity rec-
ognition: word-level vs. character-level. In: International conference of the Pacific Association for
Computational Linguistics. Springer, pp 219–232
Piryani R, Madhavi D, Singh VK (2017) Analytical mapping of opinion mining and sentiment analysis
research during 2000–2015. Inf Process Manag 53(1):122–150
Plank B, Søgaard A, Goldberg Y (2016) Multilingual part-of-speech tagging with bidirectional long short-
term memory models and auxiliary loss. arXiv preprint arXiv:​16040​5529
Poria S, Cambria E, Winterstein G, Huang GB (2014) Sentic patterns: dependency-based rules for concept-
level sentiment analysis. Knowl-Based Syst 69:45–63
Poria S, Chaturvedi I, Cambria E, Hussain A (2016) Convolutional MKL based multimodal emotion recog-
nition and sentiment analysis. In: 2016 IEEE 16th international conference on data mining (ICDM).
IEEE, pp 439–448
Poria S, Cambria E, Hazarika D, Mazumder N, Zadeh A, Morency LP (2017) Multi-level multiple atten-
tions for contextual multimodal sentiment analysis. In: 2017 IEEE international conference on data
mining (ICDM). IEEE, pp 1033–1038
Poria S, Hussain A, Cambria E (2018a) Combining textual clues with audio-visual information for multi-
modal sentiment analysis. In: Multimodal sentiment analysis. Springer, pp 153–178
Poria S, Majumder N, Hazarika D, Cambria E, Gelbukh A, Hussain A (2018) Multimodal sentiment analy-
sis: addressing key issues and setting up the baselines. IEEE Intell Syst 33(6):17–25
Poria S, Hazarika D, Majumder N, Mihalcea R (2020) Beneath the tip of the iceberg: Current challenges
and new directions in sentiment analysis research. IEEE Trans Affect Comput
Pravalika A, Oza V, Meghana N, Kamath SS (2017) Domain-specific sentiment analysis approaches for
code-mixed social network data. In: 2017 8th international conference on computing, communication
and networking technologies (ICCCNT). IEEE, pp 1–6
Qiu G, He X, Zhang F, Shi Y, Bu J, Chen C (2010) DASA: dissatisfaction-oriented advertising based on
sentiment analysis. Expert Syst Appl 37(9):6182–6191
Quinlan JR (2014) C4. 5: programs for machine learning. Elsevier, Amsterdam
Rana TA, Cheah YN (2016) Aspect extraction in sentiment analysis: comparative analysis and survey. Artif
Intell Rev 46(4):459–483
Rao D, Ravichandran D (2009) Semi-supervised polarity lexicon induction. In: Proceedings of the 12th con-
ference of the European chapter of the ACL (EACL 2009), pp 675–682
Rao G, Huang W, Feng Z, Cong Q (2018) LSTM with sentence representations for document-level senti-
ment classification. Neurocomputing 308:49–57
Ravi K, Ravi V (2015) A survey on opinion mining and sentiment analysis: tasks, approaches and applica-
tions. Knowl-Based Syst 89:14–46
Razon A, Barnden J (2015) A new approach to automated text readability classification based on concept
indexing with integrated part-of-speech n-gram features. In: Proceedings of the international confer-
ence recent advances in natural language processing, pp 521–528
Remus R (2013) Modeling and representing negation in data-driven machine learning-based sentiment anal-
ysis. In: ESSEM@ AI* IA, pp 22–33
Revathy R, Lawrance R (2017) Comparative analysis of c4. 5 and c5. 0 algorithms on crop pest data. Int J
Innovative Res Comput Commun Eng 5(1):50–58
Ritter A, Etzioni O, Clark S (2012) Open domain event extraction from twitter. In: Proceedings of the 18th
ACM SIGKDD international conference on Knowledge discovery and data mining, pp 1104–1112
Rizos G, Hemker K, Schuller B (2019) Augment to prevent: short-text data augmentation in deep learning
for hate-speech classification. In: Proceedings of the 28th ACM international conference on informa-
tion and knowledge management, pp 991–1000
Rognone L, Hyde S, Zhang SS (2020) News sentiment in the cryptocurrency market: an empirical compari-
son with forex. Int Rev Financ Anal 69:101462
Ruffer N, Knitza J, Krusche M (2020) # Covid4Rheum: an analytical twitter study in the time of the
COVID-19 pandemic. Rheumatol Int 40(12):2031–2037
Rui H, Liu Y, Whinston A (2013) Whose and what chatter matters? The effect of tweets on movie sales.
Decis Support Syst 55(4):863–870
Salah Z, Al-Ghuwairi ARF, Baarah A, Aloqaily A, Qadoumi B, Alhayek M, Alhijawi B (2019) A systematic
review on opinion mining and sentiment analysis in social media. Int J Bus Inf Syst 31(4):530–554

13
 5778 M. Wankhade et al.

Sánchez-Rada JF, Iglesias CA (2019) Social context in sentiment analysis: formal definition, overview of
current trends and framework for comparison. Inf Fusion 52:344–356
Sann R, Lai PC (2020) Understanding homophily of service failure within the hotel guest cycle: applying
NLP-aspect-based sentiment analysis to the hospitality industry. Int J Hosp Manag 91:102678
Saunders D (2021) Domain adaptation for neural machine translation. PhD thesis, University of Cambridge
Schouten K, Frasincar F (2015) Survey on aspect-level sentiment analysis. IEEE Trans Knowl Data Eng
28(3):813–830
Sharma A, Lyons J, Dehzangi A, Paliwal KK (2013) A feature extraction technique using bi-gram probabili-
ties of position specific scoring matrix for protein fold recognition. J Theor Biol 320:41–46
Shayaa S, Jaafar NI, Bahri S, Sulaiman A, Wai PS, Chung YW, Piprani AZ, Al-Garadi MA (2018) Senti-
ment analysis of big data: methods, applications, and open challenges. IEEE Access 6:37807–37827
Singh JP, Irani S, Rana NP, Dwivedi YK, Saumya S, Roy PK (2017) Predicting the “helpfulness’’ of online
consumer reviews. J Bus Res 70:346–355
Singh K, Sen I, Kumaraguru P (2018) A twitter corpus for Hindi-English code mixed POS tagging. In:
Proceedings of the sixth international workshop on natural language processing for social media, pp
12–17
Singh M, Jakhar AK, Pandey S (2021) Sentiment analysis on the impact of coronavirus in social life using
the BERT model. Soc Netw Anal Min 11(1):1–11
Singh RK, Sachan MK, Patel R (2021) 360 degree view of cross-domain opinion classification: a survey.
Artif Intell Rev 54(2):1385–1506
Singh S, Gupta P (2014) Comparative study id3, cart and c4. 5 decision tree algorithm: a survey. Int J Adv
Inf Sci Technol 27(27):97–103
Socher R, Perelygin A, Wu J, Chuang J, Manning CD, Ng AY, Potts C (2013) Recursive deep models for
semantic compositionality over a sentiment treebank. In: Proceedings of the 2013 conference on
empirical methods in natural language processing, pp 1631–1642
Soleymani M, Garcia D, Jou B, Schuller B, Chang SF, Pantic M (2017) A survey of multimodal senti-
ment analysis. Image Vis Comput 65:3–14
Stappen L, Schuller B, Lefter I, Cambria E, Kompatsiaris I (2020) Summary of MuSe 2020: multimodal
sentiment analysis, emotion-target engagement and trustworthiness detection in real-life media.
In: Proceedings of the 28th ACM international conference on multimedia, pp 4769–4770
Straka M, Hajic J, Straková J (2016) UDPipe: trainable pipeline for processing CoNLL-U files perform-
ing tokenization, morphological analysis, pos tagging and parsing. In: Proceedings of the tenth
international conference on language resources and evaluation (LREC’16), pp 4290–4297
Subhashini L, Li Y, Zhang J, Atukorale AS, Wu Y (2021) Mining and classifying customer reviews: a
survey. Artif Intell Rev 54:6343–6389
Sun C, Huang L, Qiu X (2019) Utilizing BERT for aspect-based sentiment analysis via constructing aux-
iliary sentence. arXiv preprint arXiv:​19030​9588
Taboada M, Brooke J, Tofiloski M, Voll K, Stede M (2011) Lexicon-based methods for sentiment analy-
sis. Comput Linguist 37(2):267–307
Thet TT, Na JC, Khoo CS (2010) Aspect-based sentiment analysis of movie reviews on discussion
boards. J Inf Sci 36(6):823–848
Tian Y, Galery T, Dulcinati G, Molimpakis E, Sun C (2017) Facebook sentiment: reactions and emo-
jis. In: Proceedings of the fifth international workshop on natural language processing for social
media, pp 11–16
Tran T, Ba H, Huynh VN (2019) Measuring hotel review sentiment: an aspect-based sentiment analy-
sis approach. In: International symposium on integrated uncertainty in knowledge modelling and
decision making. Springer, pp 393–405
Tripathy A, Agrawal A, Rath SK (2015) Classification of sentimental reviews using machine learning
techniques. Procedia Comput Sci 57:821–829
Tubishat M, Idris N, Abushariah MA (2018) Implicit aspect extraction in sentiment analysis: review,
taxonomy, oppportunities, and open challenges. Inf Process Manag 54(4):545–563
Turney PD, Littman ML (2003) Measuring praise and criticism: inference of semantic orientation from
association. ACM Trans Inf Syst 21(4):315–346
Uysal AK, Murphey YL (2017) Sentiment classification: feature selection based approaches versus deep
learning. In: 2017 IEEE international conference on computer and information technology (CIT).
IEEE, pp 23–30
Valdivia A, Luzíón MV, Herrera F (2017) Neutrality in the sentiment analysis problem based on fuzzy
majority. In: 2017 IEEE international conference on fuzzy systems (FUZZ-IEEE). IEEE, pp 1–6
Valdivia A, Luzón MV, Cambria E, Herrera F (2018) Consensus vote models for detecting and filtering
neutrality in sentiment analysis. Inf Fusion 44:126–135

13
A survey on sentiment analysis methods, applications, and… 5779

Valencia F, Gómez-Espinosa A, Valdés-Aguirre B (2019) Price movement prediction of cryptocurren-

cies using sentiment analysis and machine learning. Entropy 21(6):589
Van de Camp M, Van den Bosch A (2012) The socialist network. Decis Support Syst 53(4):761–769
Varelas G, Voutsakis E, Raftopoulou P, Petrakis EG, Milios EE (2005) Semantic similarity methods
in wordnet and their application to information retrieval on the web. In: Proceedings of the 7th
annual ACM international workshop on Web information and data management, pp 10–16
Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017)
Attention is all you need. arXiv preprint arXiv:​17060​3762
Vateekul P, Koomsubha T (2016) A study of sentiment analysis using deep learning techniques on Thai
twitter data. In: 2016 13th international joint conference on computer science and software engi-
neering (JCSSE). IEEE, pp 1–6
Vechtomova O (2017) Disambiguating context-dependent polarity of words: an information retrieval
approach. Inf Process Manag 53(5):1062–1079
Venugopalan M, Gupta D (2015) Exploring sentiment analysis on twitter data. In: 2015 eighth interna-
tional conference on contemporary computing (IC3). IEEE, pp 241–247
Vijay D, Bohra A, Singh V, Akhtar SS, Shrivastava M (2018) Corpus creation and emotion prediction
for Hindi-English code-mixed social media text. In: Proceedings of the 2018 conference of the
North American chapter of the Association for Computational Linguistics: student research work-
shop, pp 128–135
Wadawadagi R, Pagi V (2020) Sentiment analysis with deep neural networks: comparative study and
performance assessment. Artif Intell Rev 53:6155–6195
Wang G, Sun J, Ma J, Xu K, Gu J (2014) Sentiment classification: the contribution of ensemble learning.
Decis Support Syst 57:77–93
Wang Z, Ho SB, Cambria E (2020) Multi-level fine-scaled sentiment sensing with ambivalence han-
dling. Int J Uncertain Fuzziness Knowl-Based Syst 28(04):683–697
Wankhade M, Annavarapu CSR, Verma MK (2021) CBVoSD: context based vectors over sentiment domain
ensemble model for review classification. J Supercomput 1–37
Weerasooriya T, Perera N, Liyanage S (2016) A method to extract essential keywords from a tweet using
NLP tools. In: 2016 sixteenth international conference on advances in ICT for emerging regions
(ICTer). IEEE, pp 29–34
Wilson T, Wiebe J, Hoffmann P (2009) Recognizing contextual polarity: an exploration of features for
phrase-level sentiment analysis. Comput Linguist 35(3):399–433
Wu D, Chi M (2017) Long short-term memory with quadratic connections in recursive neural networks for
representing compositional semantics. IEEE Access 5:16077–16083
Wu P, Li X, Shen S, He D (2020) Social media opinion summarization using emotion cognition and convo-
lutional neural networks. Int J Inf Manag 51:101978
Xia H, Yang Y, Pan X, Zhang Z, An W (2020) Sentiment analysis for online reviews using conditional ran-
dom fields and support vector machines. Electron Commer Res 20(2):343–360
Xia Y, Cambria E, Hussain A, Zhao H (2015) Word polarity disambiguation using Bayesian model and
opinion-level features. Cognit Comput 7(3):369–380
Xing FZ, Cambria E, Welsch RE (2018) Natural language based financial forecasting: a survey. Artif Intell
Rev 50(1):49–73
Yadav A, Vishwakarma DK (2020) Sentiment analysis using deep learning architectures: a review. Artif
Intell Rev 53(6):4335–4385
Yan-Yan Z, Bing Q, Ting L (2010) Integrating intra-and inter-document evidences for improving sentence
sentiment classification. Acta Autom Sinica 36(10):1417–1425
Yang B, Cardie C (2014) Context-aware learning for sentence-level sentiment analysis with posterior regu-
larization. In: Proceedings of the 52nd annual meeting of the association for computational linguistics
(Volume 1: Long Papers), pp 325–335
Yaseen Q et  al (2021) Spam email detection using deep learning techniques. Procedia Comput Sci
184:853–858
Yousif A, Niu Z, Tarus JK, Ahmad A (2019) A survey on sentiment analysis of scientific citations. Artif
Intell Rev 52(3):1805–1838
Yuan Z, Wu S, Wu F, Liu J, Huang Y (2018) Domain attention model for multi-domain sentiment classifica-
tion. Knowl-Based Syst 155:1–10
Yue L, Chen W, Li X, Zuo W, Yin M (2019) A survey of sentiment analysis in social media. Knowl Inf Syst
60(2):617–663
Zhang Z, Wang L, Zou Y, Gan C (2018) The optimally designed dynamic memory networks for targeted
sentiment classification. Neurocomputing 309:36–45

13
 5780 M. Wankhade et al.

Zhao W, Guan Z, Chen L, He X, Cai D, Wang B, Wang Q (2017) Weakly-supervised deep embedding for
product review sentiment analysis. IEEE Trans Knowl Data Eng 30(1):185–197
Zhao Y, Xu X, Wang M (2019) Predicting overall customer satisfaction: Big data evidence from hotel online
textual reviews. Int J Hosp Manag 76:111–121
Zhu X, Goldberg AB (2009) Introduction to semi-supervised learning. Synth Lect Artif Intell Mach Learn
3(1):1–130
Zuo E, Zhao H, Chen B, Chen Q (2020) Context-specific heterogeneous graph convolutional network for
implicit sentiment analysis. IEEE Access 8:37967–37975
Zvarevashe K, Olugbara OO (2018) A framework for sentiment analysis with opinion mining of hotel
reviews. In: 2018 Conference on information communications technology and society (ICTAS).
IEEE, pp 1–4

Publisher’s Note  Springer Nature remains neutral with regard to jurisdictional claims in published maps and
institutional affiliations.

13