Scribd
Upload
4 views

Minor_Project_Presentation (1)

The document presents a sentiment analysis project that utilizes advanced methodologies and automation to enhance accuracy, real-time processing, and multilingual support. It outlines the project's objectives, motivation, methodology, and future plans while acknowledging contributors and data sources. The approach aims to provide businesses with actionable insights by effectively interpreting emotions and monitoring sentiment trends.

Uploaded by

kashinathkaran666
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
4 views

Minor_Project_Presentation (1)

The document presents a sentiment analysis project that utilizes advanced methodologies and automation to enhance accuracy, real-time processing, and multilingual support. It outlines the project's objectives, motivation, methodology, and future plans while acknowledging contributors and data sources. The approach aims to provide businesses with actionable insights by effectively interpreting emotions and monitoring sentiment trends.

Uploaded by

kashinathkaran666
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 16

Revolutionizing Sentiment Analysis

Through Smart Automation


Presented by:
Guided by:
Hrishav Das
Dr. Hirak
Mazumdar Indrajit
(Associate
ADAMAS University, Kolkata, India
Banerjee
Professor)
Rupankar
Halder
School of Engineering and
Technology
Department of Computer Science and Engineering
We extend our heartfelt gratitude to everyone who contributed to
the successful completion of this sentiment analysis project.

First, we would like to express our sincere thanks to Dr. Hirak


Mazumdar for their invaluable guidance, constructive feedback,
and unwavering support throughout the project's
development.

Special thanks to the team members who collaborated tirelessly, ensuring the
project stayed
on track and met its objectives.

Lastly, we acknowledge the data providers and open-source


communities whose contributions formed the backbone of our
analysis. Without their datasets, frameworks, and tools, this project
would not have been possible.

Thank you all for being part of this journey.


Content
 Introduction s
 Objectives

 Motivation

 Methodology & Tasks of Analysis

 Approach

 Conclusion

 Future Plan
Machine learning and NLP
• Natural Language Processing
considers linear relations between
• Artificial Intelligence defines Artificial intelligence
words; in simple cases of
intelligence by machines by
Machine understanding, we can design
performing like human actions. learning
feature extractors and select the
• Machine Learning is making Data Science
Deep entities to match for the given
predictions with statistical models by learning
intent.
recognising patterns in data without
requiring explicit instructions. Mathematics Programming
Statistics, linear algebra, Data engineering, software
• Deep Learning is also Machine calculus etc. engineering etc.

learning methods using deep


convolution neural network.

Trends in Pharmacological Sciences,40,8-15, (2019)


History of NLP

• Natural language processing (NLP) helps computers understand and use human languages.

• In the early 1900s, a Swiss linguistics professor named Ferdinand de Saussure died, and in the
process, almost deprived the world of the concept of “Language as a Science,” which eventually led
to natural language processing. From 1906 to 1911, Professor Saussure offered three courses at the
University of Geneva, where he developed an approach describing languages as “systems.” Within
the language, a sound represents a concept – a concept that shifts meaning as the context changes.

Reproduced from: https://medium.com/@jeevanchiru17/the-evolution-of-natural-language-processing-ad214cb9f6ca


Objecti
ves
Enhanced Accuracy Improve the precision of sentiment
classification by reducing human
bias and errors.

Enable real-time processing of large volumes of


data, like social media, customer feedback, or
Real-Time Analysis news articles, for immediate insights.
Provide businesses and organizations with the
ability to respond quickly to trends, crises, or
customer concerns.

Automated tools trained on diverse


Multilingual Support language datasets can accurately analyze
sentiment across multiple languages and
dialects, overcoming limitations in human
linguistic expertise.

Reduce reliance on manual labor for sentiment


Cost Efficiency tagging and analysis.
Automate repetitive tasks to free up resources
for strategic activities.
Emotion Interpretation identify emotional cues like
happiness, anger, or sadness
of a human.
Phase 1 (Major
Motivation Project)

Phase 1 (Minor
Sci Rep 14, 9603 (2024). Project)
Methodology of sentiment analysis

(positive, neutral, negative)

• Data can be collected from the internet via web scraping, social media, news channels, E-commerce websites, Forums,
Weblog, some other websites shown in above figure.
• Data Collection is the first stage in the Sentiment Analysis. Depending on task sentiment analysis of findings, text data can
be combined with other types of data like video, audio, location, etc.
Task of sentiment analysis

•Classify Text Sentiment: Determine if the sentiment is positive, negative, or


neutral.
•Extract Emotional Tone: Identify emotions like happiness, anger, or frustration
from text.
•Monitor Trends: Track changes in sentiment over time for products, services, or
brands
Phase I:
Developed Phase II
After Data Pre-processing

Before Data Pre-Processing


Accuracy Obtained
Conclusion

This methodology simplifies and improves sentiment analysis by using advanced tools, automated processes, and smart data handling. It starts with

collecting a wide variety of text data, cleaning and preparing it, and then using powerful machine learning models to understand emotions and

opinions. Automation helps make the process faster and more accurate, while real-time features allow for immediate insights. By tackling challenges

like sarcasm and cultural differences, this approach provides clear and useful results, helping businesses and researchers better understand public

feelings and make informed decisions.


Future plan
2024-25
Work schedule
November ~

Monthly period 1 2 3 4

Collect labelled text data, clean and normalize it by removing noise, and
tokenize the text for further processing.

Convert text into numerical features using methods like Bag of Words or TF-
IDF, and train a sentiment classification model such as Logistic Regression
or Naive Bayes, etc.

Assess the model's performance using evaluation metrics (e.g., accuracy,


precision, recall) and refine preprocess.

Revising the Masters thesis


References
1.Xiang Zhang’s Google Drive dir,
https://drive.google.com/drive/folders/0Bz8a_Dbh9Qhbfll6bVpmNUtUcFdjYmF2SEpmZUZUcVNiMUw1TWN6RDV3a0JHT3kxLVhVR2M?resourceke
y=0-TLwzfR2O-D2aPitmn5o9VQ
2.J. McAuley and J. Leskovec. Hidden factors and hidden topics: understanding rating dimensions with review text,
https://cs.stanford.edu/people/jure/pubs/reviews-recsys13.pdf
3.Feature extraction from text, https://scikit-learn.org/stable/modules/feature_extraction.html#text-feature-extraction
4.Kumar KN, Uma V (2021) Intelligent sentinet-based lexicon for context-aware sentiment analysis: optimized neural network for sentiment classifcation on social
media. J Supercomput 77:12801–12825
5.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
6.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
7.Rao D, Ravichandran D (2009) Semi-supervised polarity lexicon induction. In: Proceedings of the 12th conference of the European chapter of the ACL (EACL
2009), pp 675–682
8.Turney PD, Littman ML (2003) Measuring praise and criticism: inference of semantic orientation from association. ACM Trans Inf Syst 21(4):315–346
9.Zuo E, Zhao H, Chen B, Chen Q (2020) Context-specifc heterogeneous graph convolutional network for implicit sentiment analysis. IEEE Access 8:37967–37975
10.Mendon S, Dutta P, Behl A, Lessmann S (2021) A hybrid approach of machine learning and lexicons to sentiment analysis: enhanced insights from twitter data of
natural disasters. Inf Syst Front 23:1145–1168
Thank you for your attention

You might also like