Title: Sentiment Analysis

Under the guidance of Prof. Nikitha K S, Assistant Professor, Bangalore Institute of

Technology

Abstract:

With an accelerated evolution of the internet as websites, social networks, blogs, online
portals, reviews, opinions, recommendations, ratings, and feedback are generated by writers.
This writer generated sentiment content can be about books, people, hotels, products,
research, events, etc. These sentiments become very beneficial for businesses, governments,
and individuals. While this content is meant to be useful, a bulk of this writer generated
content require using the text mining techniques and sentiment analysis.

Sentiment analysis (SA) is an intellectual process of extricating user’s feelings and emotions.
It is one of the pursued field of Natural Language Processing (NLP). The evolution of
Internet based applications has steered massive amount of personalized reviews for various
related information on the Web. These reviews exist in different forms like social Medias,
blogs, Wiki or forum websites. Both travellers and customers find the information in these
reviews to be beneficial for their understanding and planning processes.

The boom of search engines like Yahoo and Google has flooded users with copious amount
of relevant reviews about specific destinations, which is still beyond human comprehension.
Sentiment Analysis poses as a powerful tool for users to extract the needful information, as
well as to aggregate the collective sentiments of the reviews. Several methods have come to
the limelight in recent years for accomplishing this task. In this paper we compare the various
techniques used for Sentiment Analysis by analysing various methodologies.

Sentiment Analysis (SA) is an ongoing field of research in text mining field. SA is the
computational treatment of opinions, sentiments and subjectivity of text. The related fields to
SA such as transfer learning, emotion detection, and building resources have attracted the
researchers. But there are several challenges facing the sentiment analysis and evaluation
process. These challenges become obstacles in analysing the accurate meaning of sentiments
and detecting the suitable sentiment polarity.
1. Introduction

Sentiment analysis uses the natural language processing (NLP), text analysis and
computational techniques to automate the extraction or classification of sentiment from
sentiment reviews. Analysis of these sentiments and opinions has spread across many fields
such as Consumer information, Marketing, books, application, websites, and Social.
Sentiment analysis becomes a hot area in decision making. The main goal of analysing
sentiment is to analyse the reviews and examine the scores of sentiments.

Sentiment analysis is the process of detecting the contextual polarity of the text. It determines
whether given text is positive, negative or neutral. It is otherwise called as opinion mining
too, since it derives the opinion or attitude of the speaker. For this analysis, the opinions are
collected from the users, which can be employed for further improvements.

Sentiment Analysis (SA) or Opinion Mining (OM) is the computational study of people’s
opinions, attitudes and emotions toward an entity. The entity can represent individuals, events
or topics. These topics are most likely to be covered by reviews.

The two expressions SA or OM are interchangeable. They express a mutual meaning.

However, some researchers stated that OM and SA have slightly different notions. Opinion
Mining extracts and analyses people’s opinion about an entity while Sentiment Analysis
identifies the sentiment expressed in a text then analyses it. Therefore, the target of SA is to
find opinions.

SA is not only applied on product reviews but can also be applied on stock markets, news
articles, or political debates. In political debates for example, we could figure out people’s
opinions on a certain election candidates or political parties. The election results can also be
predicted from political posts. The social network sites and micro-blogging sites are
considered a very good source of information because people share and discuss their opinions
about a certain topic freely. They are also used as data sources in the SA process.

This paper also discusses new related fields in SA which have attracted the researchers lately
and their corresponding articles which include Emotion Detection (ED), Building Resources
(BR) and Transfer Learning (TL). Emotion detection aims to extract and analyse emotions,
while the emotions could be explicit or implicit in the sentences. Transfer learning or Cross-
Domain classification is concerned with analysing data from one domain and then using the
results in a target domain.

2. Classification Techniques of Sentiment Analysis

Sentiment Classification techniques can be roughly divided into machine learning approach,
lexicon based approach and hybrid approach.

Fig. 2 – Sentiment Analysis Classification Techniques

The Machine Learning Approach (ML) applies the famous ML algorithms and uses linguistic
features. The Lexicon-based Approach relies on a sentiment lexicon, a collection of known
and precompiled sentiment terms. It is divided into dictionary-based approach and corpus-
based approach which use statistical or semantic methods to find sentiment polarity. The
hybrid Approach combines both approaches and is very common with sentiment lexicons
playing a key role in the majority of methods.
The text classification methods using ML approach can be roughly divided into supervised
and unsupervised learning methods. The supervised methods make use of a large number of
labelled training documents. The unsupervised methods are used when it is difficult to find
these labelled training documents.

The lexicon-based approach depends on finding the opinion lexicon which is used to analyse
the text. There are two methods in this approach. The dictionary-based approach which
depends on finding opinion seed words, and then searches the dictionary of their synonyms
and antonyms. The corpus-based approach begins with a seed list of opinion words, and then
finds other opinion words in a large corpus to help in finding opinion words.

Table 1 - Comparison of the three classification techniques

Approaches Classification Advantages Disadvantages

Machine Supervised and Dictionary is not Classifier trained

Learning learning. unsupervised necessary. on the texts in one
Approach Demonstrate the high domain in most
accuracy of cases does not
classification. work with other
domains.
Rule Based Supervised and Performance accuracy Efficiency and
Approach learning. unsupervised of 91% at the review accuracy depend
level and 86% at the
the defining rules.
sentence level.
Sentence level
sentiment
classification performs
better than the word
level.
Lexicon Unsupervised learning. Labelled data and the Requires powerful
Based procedure of learning is linguistic
Approach not required. resources which is
not always
available.
3. Levels of Sentiment Analysis

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.

Fig. 3 – Levels of 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. (Saunders 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.

Sentence-level
In this level of analysis, each sentence is analyzed and finding with a corresponding
polarity. This is highly useful when a document has a wide range and mix of sentiments
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
independently 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

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

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 single
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
document 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.

Aspect-level
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).

3. Feature Selection in Sentiment Classification

Feature selection in sentiment classification Sentiment Analysis task is considered a
sentiment classification problem. The first step in the SC problem is to extract and select text
features. Some of the current features are :
 Terms presence and frequency : These features are individual words or word n-
grams and their frequency counts. It either gives the words binary weighting (zero if
the word appears, or one if otherwise) or uses term frequency weights to indicate the
relative importance of features.
 Parts of speech (POS) : finding adjectives, as they are important indicators of
opinions. Opinion words and phrases: these are words commonly used to express
opinions including good or bad, like or hate. On the other hand, some phrases express
opinions without using opinion words. For example: cost me an arm and a leg.
 Negations : the appearance of negative words may change the opinion orientation like
not good is equivalent to bad.

Feature Selection Methods :

 The point-wise mutual information (PMI)
Mi(w) between the word w and the class i is defined on the basis of the level of co-
occurrence between the class i and word w. The expected co-occurrence of class i and
word w, on the basis of mutual independence, is given by Pi.F(w), and the true co-
occurrence is given by F(w).pi(w).
The mutual information is defined in terms of the ratio between these two values and is
given by the following equation :
F ( w ) . pi (w) pi (w)
Mi(w) = log( ¿ = log( ¿
F ( w ) . Pi Pi
 Chi-square (X2)
Let n be the total number of documents in the collection, pi(w) be the conditional
probability of class i for documents which contain w, Pi be the global fraction of
documents containing the class i, and F(w) be the global fraction of documents which
contain the word w. Therefore, the v2 -statistic of the word between word w and class i is
defined as :
n . F (w)2 .( pi ( w ) −Pi )2
Xi2 =
F ( w ) . ( 1−F ( w )) . Pi .(1−Pi )

4. Sentiment Analysis for Sinhala Language using Deep Learning

Techniques
Sentiment analysis, a burgeoning field in natural language processing, has witnessed
remarkable progress with the advent of deep learning techniques such as Convolutional
Neural Networks (CNNs) and Recurrent Neural Networks (RNNs). While these
advancements have primarily been observed in high-resourced languages like English, the
domain presents unique challenges when applied to under-resourced languages such as
Sinhala, a morphologically rich Indo-Aryan language. This summary encapsulates the
evolution, challenges, and recent advancements in sentiment analysis for Sinhala,
highlighting key research contributions and future directions.

The passage begins by contextualizing the development of sentiment analysis, attributing its
success to deep learning techniques that treat text as sequences or spatial patterns, enabling
the modeling of higher-level concepts beyond word meanings. However, the application of
these techniques to Sinhala poses significant hurdles, primarily stemming from the language's
under-resourced nature and the scarcity of annotated corpora. While deep learning methods
like LSTM and CNN have been explored in previous studies, their efficacy has been limited
by the lack of large annotated datasets and language-specific features.

Recognizing these challenges, recent research endeavors have aimed to address the
limitations of sentiment analysis in Sinhala by conducting comprehensive empirical studies
and introducing novel datasets. One such study presented in the passage expands sentiment
analysis in Sinhala from binary to four categories—positive, negative, neutral, and conflict. It
explores a diverse array of deep learning models, including RNN, LSTM, Bi-LSTM,
hierarchical attention hybrid neural networks, and capsule networks, aiming to enhance the
accuracy and robustness of sentiment analysis for Sinhala text.

As mentioned earlier, Sinhala does not have well-developed linguistic resources such as
sentiment lexicons. Thus, deep learning techniques that used such auxiliary information could
not be applied. Similarly, BERT based techniques could not be applied as Sinhala does not
have a pre-trained model and we did not have the capacity to build one. Therefore, to begin
with, well-known deep learning models such as RNN, LSTM, GRU, and BiLSTM were
applied to perform sentiment analysis on our data set.

5. Applications of Sentiment Analysis

Sentiment analysis has many applications, ranging from analysing customer opinion,
analysing 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
practically any discipline. A few significant domains and industries where Sentiment
Analysis is applied are described below:

Fig. 4 – Applications of Sentiment Analysis

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 analysis in the
field of business intelligence is analysing 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 business intelligence
has various benefits. For example, Businesses can use the results of Sentiment Analysis to
make product enhancements, examine consumer feedback, or develop a new marketing plan
(Han et al. 2019).

Healthcare and medical domain

This is one of the industries where sentiment analysis is being utilized in recent times. This
application helps healthcare service providers collect and evaluate patient moods, epidemics,
adverse drug reactions, and diseases to improve healthcare services. 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, rallying support, and expanding public awareness
were all linked. In conclusion, applying sentiment analysis to analyse patient-generated data
on social media can help determine patients’ needs and views.

Review Analysis
Sentiment analysis is extensively used in the domain of Entertainment. Reviews of movie,
shows, and short films may be analysed 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 developing machine learning and online
consumer recommendation systems based on intelligent, data-driven decision-making
techniques (Jain et al. 2021f) also discussed categorising consumer decisions as positive or
negative based on online reviews provided by the valuable consumer(Jain et al. 2021e).

Stock Market
One of the applications of sentiment analysis is stock price prediction. It can be done by
analysing 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. Sentence level
sentiment analysis can be done on these texts, after which the overall polarity of texts will be
decided of news of a particular company. 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 analysis to
anticipate the value of digital cryptocurrencies.

6. Challenges of 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.

Fig. 5 – SA Challenge Types and Techniques Used

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.

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 dependent 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).
Unstructured Sentiments
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 multiple
sentences, each of which could potentially include both pros and cons. For example,
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 sentence’s
segment/chunk, the feature is referred to as an explicit feature of the product. For instance, in
the segment, the image is marvellous. 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 critical nature of sentiment
analysis, this study examines the relationship between respondents perspective structures and
sentiment analysis issues.

Methodological Sentiments
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. Numerous methods have been proposed
(Castro et al. 2019; Medhat et al. 2014) for detecting 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 frequently 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.

7. Conclusion
In conclusion, sentiment analysis stands as a powerful tool for understanding and interpreting
human emotions expressed through textual data. Through the utilization of machine learning
and natural language processing techniques, sentiment analysis algorithms can effectively
classify text into positive, negative, or neutral sentiments, enabling businesses to gain
valuable insights into customer opinions, market trends, and brand reputation.

However, challenges such as context ambiguity, sarcasm, and language nuances persist,
highlighting the need for ongoing research and refinement of sentiment analysis
methodologies. Nevertheless, the continued advancement of sentiment analysis holds
immense potential for enhancing decision-making processes across various industries, driving
innovation, and ultimately improving user experiences.

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 challenges encountered and the most common application areas are discussed then
the survey examines the significance and consequences of sentiment analysis challenges in
sentiment evaluation. The comparison investigates the relationship between the structure of
sentiment reviews and the difficulties associated with sentiment analysis. This comparison
reveals domain dependence, essential for identifying sentiment issues. The future work will
consist of continuously expanding the comparison area with additional findings. The
subsequent challenges illustrate that sentiment analysis is still a relatively unexplored subject
of study.

References
[1] Tsytsarau Mikalai, Palpanas Themis. Survey on mining subjective data on the web. Data
Min Knowl Discov 2012;24:478–514.

[2] Wilson T, Wiebe J, Hoffman P. Recognizing contextual polarity in phrase-level sentiment

analysis. In: Proceedings of HLT/ EMNLP; 2005.

[3] Liu B. Sentiment analysis and opinion mining. Synth Lect Human Lang Technol 2012.

[4] Yu Liang-Chih, Wu Jheng-Long, Chang Pei-Chann, Chu Hsuan-Shou. Using a contextual

entropy model to expand emotion words and their intensity for the sentiment classification of
stock market news. Knowl-Based Syst 2013;41:89–97.

[5] Michael Hagenau, Michael Liebmann, Dirk Neumann. Automated news reading: stock
price prediction based on financial news using context-capturing features. Decis Supp Syst;
2013.

[6] Tao Xu, Peng Qinke, Cheng Yinzhao. Identifying the semantic orientation of terms using
S-HAL for sentiment analysis. KnowlBased Syst 2012;35:279–89.
[7] Maks Isa, Vossen Piek. A lexicon model for deep sentiment analysis and opinion mining
applications. Decis Support Syst 2012;53:680–8.

[8] Pang B, Lee L. Opinion mining and sentiment analysis. Found Trends Inform Retriev
2008;2:1–135.

[9] Cambria E, Schuller B, Xia Y, Havasi C. New avenues in opinion mining and sentiment
analysis. IEEE Intell Syst 2013;28:15–21.

[10] Feldman R. Techniques and applications for sentiment analysis. Commun ACM
2013;56:82–9.
[11] Montoyo Andre´s, Martı´nez-Barco Patricio, Balahur Alexandra. Subjectivity and
sentiment analysis: an overview of the current state of the area and envisaged developments.
Decis Support Syst 2012;53:675–9.

[12] Qiu Guang, He Xiaofei, Zhang Feng, Shi Yuan, Bu Jiajun, Chen Chun. DASA:
dissatisfaction-oriented advertising based on sentiment analysis. Expert Syst Appl
2010;37:6182–91.

[13] Lu Cheng-Yu, Lin Shian-Hua, Liu Jen-Chang, Cruz-Lara Samuel, Hong Jen-Shin.
Automatic event-level textual emotion sensing using mutual action histogram between
entities. Expert Syst Appl 2010;37:1643–53.

[14] Neviarouskaya Alena, Prendinger Helmut, Ishizuka Mitsuru. Recognition of Affect,

Judgment, and Appreciation in Text. In: Proceedings of the 23rd international conference on
computational linguistics (Coling 2010), Beijing; 2010. p. 806–14.

[15] Bai X. Predicting consumer sentiments from online text. Decis Support Syst
2011;50:732–42.

[16] Zhao Yan-Yan, Qin Bing, Liu Ting. Integrating intra- and interdocument evidences for
improving sentence sentiment classification. Acta Automatica Sinica 2010;36(October’10).
[17] Yi Hu, Li Wenjie. Document sentiment classification by exploring description model of
topical terms. Comput Speech Lang 2011;25:386–403.

[18] Cao Qing, Duan Wenjing, Gan Qiwei. Exploring determinants of voting for the
‘‘helpfulness’’ of online user reviews: a text mining approach. Decis Support Syst
2011;50:511–21.

[19] He Yulan, Zhou Deyu. Self-training from labeled features for sentiment analysis. Inf
Process Manage 2011;47:606–16.

[20] Tan Songbo, Wu Qiong. A random walk algorithm for automatic construction of
domain-oriented sentiment lexicon. Expert Syst Appl 2011:12094–100.