DECODING REVIEWS:

AI-POWERED PRODUCT
REVIEW ANALYSIS

Presented by
Apurva Wankhade (23MAI0047)
Tanvi Paigude (23MAI0002)
Guided By: Dr. Anny Lemma
 Introduction
Motivation
Literature Survey
Gaps Identified
CONTENTS
Problem Statement
Salient features of the Proposed system
System Design
References
INTRODUCTION

In today's competitive business landscape, harnessing AI's power is crucial. AI-driven product

review analysis, utilizing Natural Language Processing (NLP), extracts vital insights from

customer feedback. NLP-based sentiment analysis gauges customer emotions, identifying

positive and negative sentiments, and providing a deeper understanding of satisfaction levels.

This research aims to offer invaluable insights, aiding efficient product development and

marketing decisions. It also extends to competitive analysis, revealing rivals' strengths and

weaknesses. In a world where time and resources are precious, our methodology promises to

transform customer feedback analysis, saving both time and money and reshaping how

companies respond to their customers' voices.

MOTIVATION

Increase in Online Difficulty in Manual Lack of Actionable

Product Reviews Analysis Insights

The exponential growth of Analyzing large volumes of Traditional analysis methods

online shopping has led to product reviews manually is often fail to extract valuable
an increase in the number time-consuming and prone insights from product
of product reviews to human error. reviews.
available.
 LITERATURE
Sr. No. Authors/Year
SURVEY
Journal/Conference Title Methodology Algorithm
Papers
1. L. Yang, Y. Li, J. Wang, IEEE Access Sentiment Analysis for SLCABG model for CNN, GRU
and R. S. Sherratt E-Commerce Product sentiment analysis is used
(2020) Reviews in Chinese along with CNN and GRU
Based on Sentiment to extract main sentiment
Lexicon and Deep features in the reviews.
Learning

2. Wei Zhao, Ziyu Guan, IEEE Access Weakly-Supervised Performs opinion mining CNN, LSTM
Long Chen (2018) Deep Embedding for using CNN and LSTM and
Product Review synthesizing the extracted
Sentiment Analysis features.

3. Syed Afeef Ahmed IEEE Access Dark Web: E- Uses Bi-directional LSTM CNN, LSTM
Shah , Muhammad Ali Commerce Information and CNN for information
Masood, And Extraction Based on extraction on Dark web
Amanullah Yasin (2020) Name Entity dataset , achieving a
Recognition Using 96.20% accuracy.
Bidirectional-LSTM
4. Devika M D, Sunitha Procedia Computer Sentiment Analysis: A Compares different SVM, Naïve Bayes’ , N-
C, Amal Ganesh Science Comparative Study on approaches for gram model.
(2018) Different Approaches. sentiment analysis.

5. Apoorv Agarwal,Boyi Procedia Computer Sentiment Analysis of POS tagging and unigram Unigram Model
Xie, Ilia Vovsha, Owen Science Twitter Data models used to combine
Rambow, Rebecca prior polarity of words
Passonneau (2020) with their part of speech.

6. Zhenyu Zhang, Jian Journal of Complex Product selection intuitionistic fuzzy TODIM method
Guo, Huirong Zhang, and Intelligent Systems based on sentiment TODIM method is used
Lixin Zhou, Mengjiao analysis of online to determine the
Wang (2022) reviews: ranking results of the
an intuitionistic fuzzy alternative products.
TODIM method
7. Su Su Htay, Khin Thidar Lynn (2018) Hindawi Extracting Product Uses a part-of-speech tagger to POS tagging
Scientific Journal Features and Opinion identify phrases in the
Words Using Pattern input text that contains adjective or
Knowledge in Customer adverb or verb or
Reviews nouns as opinion phrases.
8. Sanjay Dey, Sarhan Wasif, Dhiman IEEE Access A comparative study of Compares SVM and naïve bayes SVM, Naïve Bayes’
Sikder Tonmoy (2020) SVM and NB classifier for classifier for sentiment analysis.
Sentiment Analysis on
Amazon Product
Reviews.

9. Oscar Araque,Ignacio Corcuera- International Enhancing deep learning Uses an ensemble of classifiers where Ensemble classifiers
Platas, J. Fernando Sánchez-Rada, Conference on sentiment analysis with several sentiment classifiers draw
Carlos A. Iglesias. Computing, ensemble techniques insights from six public datasets.
Communication in social applications
and
Automation(IEE
E)

10. Erica Cambria, Catherine Proceedings of SenticNet 2: A Semantic Compares different approaches for CF-IOF
Havasi,Amir Hussain 25th and Affective Resource sentiment analysis.
International for Opinion Mining and
Florida Aritificial Sentiment Analysis
Intelligence
Research
Society
Conference(Scie
nceDirect)
GAPS IDENTIFIED

• No gain pts: Gain points are the positive or beneficial aspects of a product or service that
customers appreciate. These are the features or qualities that make customers happy and
satisfied.
• No pain pts: Pain points are the negative or frustrating aspects of a product or service that
customers find problematic or unsatisfactory. These are the features or qualities that can
lead to customer dissatisfaction or frustration.
PROBLEM STATEMENT

• The growing field of AI-powered product review analysis aims to leverage artificial intelligence
techniques to extract valuable insights from customer reviews across various products.
• These insights are crucial for improving product development, enhancing marketing strategies,
and elevating customer service.
• This proposed solution aims at using a web crawler to extract product reviews and draw
insights about features and quality of the product using AI techniques, that will help the
business to improve the product quality. It conducts feature-wise comparisons using the seq-2-
seq model, pinpointing specific product features that drive satisfaction or dissatisfaction.
SALIENT FEATURES OF THE PROPOSED SYSTEM

• Evaluate reviews to identify positive and negative sentiments linked to particular product
features, known as strengths and weaknesses.
• To assess competitors' products to gain insights into their pros and cons.

• To uncover the most frequently discussed aspects of products, enabling businesses to

better comprehend customer opinions and preferences for more informed decision-
making and resource allocation.
SYSTEM DESIGN
 DESIGN STAGES

1
Web Scrapping Aspect-based Sentiment Opinion
Click on the "Canva" button Analysis Mining
next to this presentation.
Start editing your
Scrapping theYou
presentation. webmay need
Aspect-based Opinion mining
to sign in to your Canva
page data sentiment analysis techniques can
account.
consisting of can identify specific extract subjective
product reviews aspects of a product information from
mentioned in reviews product reviews,
and analyze including user
sentiment towards preferences and
each aspect. sentiments.
SEQUENCE-2-SEQUENCE
LSTM ARCHITECTURE
REFERENCES
1. L. Yang, Y. Li, J. Wang, and R. S. Sherratt, "Sentiment Analysis for E-Commerce Product Reviews in Chinese
Based on Sentiment Lexicon and Deep Learning," in IEEE Access, vol. 8, pp. 23522-23530, 2020, doi:
10.1109/ACCESS.2020.2969854.
2. W. Zhao et al., "Weakly-Supervised Deep Embedding for Product Review Sentiment Analysis," in IEEE
Transactions on Knowledge and Data Engineering, vol. 30, no. 1, pp. 185-197, 1 Jan. 2018, doi:
10.1109/TKDE.2017.2756658.
3. S. A. A. Shah, M. Ali Masood, and A. Yasin, "Dark Web: E-Commerce Information Extraction Based on Name
Entity Recognition Using Bidirectional-LSTM," in IEEE Access, vol. 10, pp. 99633-99645, 2022, doi:
10.1109/ACCESS.2022.3206539.
4. Doaa Mohey El-Din Mohamed Hussein, A survey on sentiment analysis challenges, Journal of King Saud
University – Engineering Sciences, Volume30, Issue 4, 2018, Pages 330-338, ISSN 1018-3639,
5. Zhang, Z., Guo, J., Zhang, H. et al. Product selection based on sentiment analysis of online reviews: an
intuitionistic fuzzy TODIM method. Complex Intell. Syst. 8, 3349–3362 (2022).
6. 13. S. Dey, S. Wasif, D. S. Tonmoy, S. Sultana, J. Sarkar, and M. Dey, "A Comparative Study of Support Vector
Machine and Naive Bayes Classifier for Sentiment Analysis on Amazon Product Reviews," 2020 International
Conference on Contemporary Computing and Applications (IC3A), Lucknow, India, 2020.
7. SenticNet 2: A semantic and affective resource for opinion mining and sentiment analysis, Proceedings of
the 25th International Florida Artificial Intelligence Research Society Conference, FLAIRS-25.
8. Htay SS, Lynn KT. Extracting product features and opinion words using pattern knowledge in customer
reviews. ScientificWorldJournal. 2013 Dec 26;2013:394758. doi: 10.1155/2013/394758. PMID: 24459430;
PMCID: PMC3888732.
9. C. Chauhan and S. Sehgal, "Sentiment analysis on product reviews," 2017 International Conference on
Computing, Communication and Automation (ICCCA), Greater Noida, India, 2017, pp. 26-31, doi:
10.1109/CCAA.2017.8229825.
10. M.D. Devika, C. Sunitha, Amal Ganesh, Sentiment Analysis: A Comparative Study on Different Approaches,
Procedia Computer Science, Volume 87, 2016, Pages 44-49, ISSN 1877-0509
11. Kavanagh, James, Greenhow, Keith and Jordanous, Anna (2023) Assessing the Effects of Lemmatisation
and Spell Checking on Sentiment Analysis of Online Reviews. In: 17th IEEE International Conference on
SEMANTIC COMPUTING (ICSC), 1-3 Feb 2023, Laguna Hills, USA.
12. Apoorv Agarwal, Boyi Xie, Ilia Vovsha, Owen Rambow, and Rebecca Passonneau. 2011. Sentiment analysis
of Twitter data. In Proceedings of the Workshop on Languages in Social Media (LSM '11). Association for
Computational Linguistics, USA, 30–38.
13. Conference Proceedings, Subjectivity Word Sense Disambiguation Akkaya, Cem, Wiebe, Janyce, Mihalcea,
Rada, Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing,
Association for Computational Linguistics.
14. Kim, S. G., & Kang, J. (2018). Analyzing the discriminative attributes of products using text mining focused
on cosmetic reviews. Information Processing & Management, 54(6), 938-957.
15. Perwej, Dr. Yusuf & Divya, Km & Rastogi, Dr & Yadav, Puneet. (2022). Sentimental Analysis on Web
Scraping Using Machine Learning Method. Journal of Information and Computational Science. Volume 12.
10.12733/JICS.2022/V12I08.535569.67004.
16. M. S. Parvez, K. S. A. Tasneem, S. S. Rajendra and K. R. Bodke, "Analysis Of Different Web Data Extraction
Techniques," 2018 International Conference on Smart City and Emerging Technology (ICSCET), Mumbai,
India, 2018, pp. 1-7, doi: 10.1109/ICSCET.2018.8537333.
17. Zhang, L., Wang, S., & Liu, B. (2018). Deep learning for sentiment analysis: A survey. Wiley Interdisciplinary
Reviews: Data Mining and Knowledge Discovery, 8(4), e1253. doi:10.1002/widm.1253.
18. Haque, T. U., Saber, N. N., & Shah, F. M. (2018). Sentiment analysis on large scale Amazon product
reviews. 2018 IEEE International Conference on Innovative Research and Development (ICIRD).
doi:10.1109/icird.2018.8376299.
THANK YOU