A Review on Sentiment Classification of Amazon Product Review Dataset using NLP Techniques

Abstract

With an emphasis on its applicability to research into consumer behaviour and online shopping, this review paper examines recent developments and methods for sentiment categorisation. With the proliferation of online marketplaces comes an increased need for user-generated material, particularly product reviews, and the realisation that thorough sentiment analysis aids buyers in making informed purchases. The study delves into a number of To classify sentiments using natural language processing techniques, one can use either traditional or deep learning models, such as Support Vector Machines (SVMs), Decision Trees, Naive Bayes, or Convolutional Neural Networks (CNNs) or Long Short-Term Memory networks (LSTMs). One of the most important feature extraction procedures in \"translating textual input into suitable forms for sentiment analysis\" is word embeddings. Other approaches include Bag of Words (BoW), and Term Frequency-Inverse Document Frequency (TF-IDF). Tokenising, stemming, and stop word elimination are preprocessing techniques included in the review as well. These are essential for improving the input data quality and the model\'s performance. This study highlights some of the major challenges and restrictions of sentiment classification, such as the following: sarcasm detection; negation handling; and training set internal biases. I would like to emphasise the importance of explainable artificial intelligence in enhancing confidence in sentiment analysis applications, especially in significant corporate settings. Using contextualised word embeddings, multimodal sentiment analysis, and the development of domain-specific models matching industry-specific demands are some of the future breakthroughs in natural language processing (NLP) that the paper discusses. Learning systems must be constantly adapting to reflect client opinions and language growth. Focussing on its importance in enhancing consumer experiences and directing strategic business decisions in the dynamic digital market, this review aims to provide a comprehensive view of sentiment classification\'s current state and future prospects.

Introduction

1. Importance of Sentiment Analysis in E-Commerce:
Sentiment analysis, or opinion mining, is key in interpreting consumer opinions from unstructured text, such as Amazon product reviews. It helps companies understand customer satisfaction, brand perception, and improve marketing and product strategies.

2. Challenges in Sentiment Classification:
Sentiment analysis faces difficulties including sarcasm, irony, context sensitivity, domain-specific language, language ambiguity, and class imbalance in datasets.

3. Techniques Used:

• Text Representation: BoW, TF-IDF, and word embeddings (Word2Vec, GloVe, FastText).

• Feature Extraction: N-grams, sentiment lexicons.

• Machine Learning Models: Naive Bayes, SVM, Logistic Regression, Random Forest.

• Deep Learning Models: LSTM, GRU, CNN, BERT, Transformer-based models.

• Hybrid & Ensemble Approaches: Combining ML and DL methods to boost accuracy and robustness.

• Preprocessing Techniques: Tokenization, stop word removal, stemming, lemmatization.

4. Related Work:
Recent research has explored:

• Emoji-based multi-view sentiment models.

• URL-based review scraping and analysis using LSTM/GRU.

• Transfer learning with models like BERT for domain adaptation.

• Comparative reviews of traditional vs deep learning methods.

• Applications in high-stakes sectors like logistics and finance.

5. Current Limitations:

• Inadequate handling of context and sarcasm.

• Poor generalization across domains.

• Data imbalance issues skewing model predictions.

6. Future Trends:

• Context-aware embeddings (BERT, GPT).

• Multimodal sentiment analysis (text + images/videos).

• Explainable AI for transparent models.

• Domain-specific sentiment models.

• Continual learning for evolving language trends.

• Emotion detection beyond binary classification.

• Ethical AI and bias mitigation.

• Advanced preprocessing and cross-lingual sentiment analysis.

Conclusion

Natural Language Processing (NLP) sentiment classification is rapidly expanding in importance, particularly for e-commerce and online customer interactions. Through accurate analysis and interpretation of customer attitudes from massive volumes of textual data, businesses may improve customer experiences, influence product offers, and allow informed decisions. But this has a lot of repercussions. This paper showcases a variety of sentiment analysis methods, including deep learning models, unique preprocessing techniques, and more typical machine learning applications. Word embeddings, TF-IDF, and the Bag of Words are a few methods that scholars and practitioners use to capture the intricacies of expressing sentiment in text. Results in classifications that are more consistent as a result. The use of transformer topologies in conjunction with contextualisedembeddings has also made great strides in the area, improving the capacity to understand language and identify sentiment. Expanding the breadth of possible sentiment classifications, multimodal sentiment analysis incorporates insights from a wide variety of data sources, including visual ones like images and videos. In contrast, the discipline faces substantial obstacles in removing biases from training data, adjusting to linguistic shifts, and guaranteeing model interpretability. As sentiment classification advances, research into emotion identification, explainable AI methods, and strong models that can function effectively across languages and domains should be prioritised. The use of sentiment analysis extends beyond e-commerce into fields such as public opinion research, social media monitoring, and customer service automation. As sentiment analysis is used increasingly often by corporations to evaluate consumer attitude, the necessity to solve ethical challenges and reduce discrimination will only increase. Collectively, new concepts and tools that aim to enhance our comprehension of human feelings and viewpoints are encouraging for the trajectory of sentiment classification in NLP. Professionals and academics might make better use of sentiment analysis in the digital era if they accepted these advancements, which would lead to more effective customer interaction strategies and decision-making.

References

[1] M. A. Sultana, R. P, S. M, and J. G, “Amazon Product Review Sentiment Analysis Using Machine Learning,” Int. Res. J. Comput. Sci., vol. 8, no. 7, pp. 136–141, 2021, doi: 10.26562/irjcs.2021.v0807.001. [2] A. S. M. AlQahtani, “Product Sentiment Analysis for Amazon Reviews,” Int. J. Comput. Sci. Inf. Technol., vol. 13, no. 3, pp. 15–30, 2021, doi: 10.5121/ijcsit.2021.13302. [3] A. Dadhich and B. Thankachan, “Sentiment Analysis of Amazon Product Reviews Using Hybrid Rule-based Approach,” Int. J. Eng. Manuf., vol. 11, no. 2, pp. 40–52, 2021, doi: 10.5815/ijem.2021.02.04. [4] 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 Int. Conf. Contemp. Comput. Appl. IC3A 2020, no. May, pp. 217–220, 2020, doi: 10.1109/IC3A48958.2020.233300. [5] R. Bose, R. K. Dey, S. Roy, and D. Sarddar, “Sentiment Analysis on Online Product Reviews,” Adv. Intell. Syst. Comput., vol. 933, no. August, pp. 559–569, 2020, doi: 10.1007/978-981-13-7166-0_56. [6] M. Syamala and N. J. Nalini, “A filter based improved decision tree sentiment classification model for real-time amazon product review data,” Int. J. Intell. Eng. Syst., vol. 13, no. 1, pp. 191–202, 2020, doi: 10.22266/ijies2020.0229.18. [7] M. H. Munna, M. R. I. Rifat, and A. S. M. Badrudduza, “Sentiment Analysis and Product Review Classification in E-commerce Platform,” ICCIT 2020 - 23rd Int. Conf. Comput. Inf. Technol. Proc., pp. 19–21, 2020, doi: 10.1109/ICCIT51783.2020.9392710. [8] M. P. Abraham, “Feature Based Sentiment Analysis of Mobile Product Reviews using Machine Learning Techniques,” Int. J. Adv. Trends Comput. Sci. Eng., vol. 9, no. 2, pp. 2289–2296, 2020, doi: 10.30534/ijatcse/2020/210922020 [9] D. Kumar, R. Aggarwal, S. Raghuvanshi, and S. Chand, “An Integrated Approach for Amazon Product Reviews Classification Using Sentiment Analysis,” Int. J. Comput. Appl. Inf. Technol., vol. 12, no. 2, p. 317, 2020, [Online]. Available: www.ijcait.com [10] S. Tammina and S. Annareddy, “Sentiment analysis on customer reviews using convolutional neural network,” 2020 Int. Conf. Comput. Commun. Informatics, ICCCI 2020, pp. 20–25, 2020, doi: 10.1109/ICCCI48352.2020.9104086. [11] D. Kumar, R. Aggarwal, S. Raghuvanshi, and S. Chand, “An Integrated Approach for Amazon Product Reviews Classification Using Sentiment Analysis,” Int. J. Comput. Appl. Inf. Technol., vol. 12, no. 2, pp. 317–324, 2020, [Online]. Available: www.ijcait.com [12] H. M. Keerthi Kumar, B. S. Harish, and H. K. Darshan, “Sentiment Analysis on IMDb Movie Reviews Using Hybrid Feature Extraction Method,” Int. J. Interact. Multimed. Artif. Intell., vol. 5, no. 5, pp. 109–114, 2019, doi: 10.9781/ijimai.2018.12.005. [13] Q. A. Xu, C. Jayne, and V. Chang, “An emoji feature-incorporated multi-view deep learning for explainable sentiment classification of social media reviews,” Technol. Forecast. Soc. Change, vol. 202, no. December 2023, p. 123326, 2024, doi: 10.1016/j.techfore.2024.123326. [14] Aakash, S. Gupta, and A. Noliya, “URL-Based Sentiment Analysis of Product Reviews Using LSTM and GRU,” Procedia Comput. Sci., vol. 235, no. 2023, pp. 1814–1823, 2024, doi: 10.1016/j.procs.2024.04.172. [15] A. A. Syed, F. L. Gaol, A. Boediman, and W. Budiharto, “Airline reviews processing: Abstractive summarization and rating-based sentiment classification using deep transfer learning,” Int. J. Inf. Manag. Data Insights, vol. 4, no. 2, p. 100238, 2024, doi: 10.1016/j.jjimei.2024.100238. [16] J. R. Jim, M. A. R. Talukder, P. Malakar, M. M. Kabir, K. Nur, and M. F. Mridha, “Recent advancements and challenges of NLP-based sentiment analysis: A state-of-the-art review,” Nat. Lang. Process. J., vol. 6, no. January, p. 100059, 2024, doi: 10.1016/j.nlp.2024.100059. [17] N. Sultana, P. Kumar, M. R. Patra, S. Chandra, and S. K. S. Alam, “Sentiment Analysis for Product Review,” Int. Res. J. Mod. Eng. Technol. Sci., vol. 6956, no. April, pp. 1913–1919, 2023, doi: 10.56726/irjmets36776. [18] M. V. Rao and C. Sindhu, “Detection of Sarcasm on Amazon Product Reviews using Machine Learning Algorithms under Sentiment Analysis,” 2021 Int. Conf. Wirel. Commun. Signal Process. Networking, WiSPNET 2021, no. October, pp. 196–199, 2021, doi: 10.1109/WiSPNET51692.2021.9419432. [19] M. Y. Ali Salmony and A. Rasool Faridi, “Supervised Sentiment Analysis on Amazon Product Reviews: A survey,” Proc. 2021 2nd Int. Conf. Intell. Eng. Manag. ICIEM 2021, pp. 132–138, 2021, doi: 10.1109/ICIEM51511.2021.9445303. [20] A. Shah, “Sentiment analysis of product reviews using supervised learning,” Reliab. Theory Appl., vol. 16, pp. 243–253, 2021, doi: 10.1145/3447568.3448513. [21] M. Hawlader, A. Ghosh, Z. K. Raad, W. A. Chowdhury, M. S. H. Shehan, and F. Bin Ashraf, “Amazon Product Reviews: Sentiment Analysis Using Supervised Learning Algorithms,” Proc. Int. Conf. Electron. Commun. Inf. Technol. ICECIT 2021, no. June, 2021, doi: 10.1109/ICECIT54077.2021.9641243. [22] S. A. Aljuhani and N. S. Alghamdi, “A comparison of sentiment analysis methods on Amazon reviews of Mobile Phones,” Int. J. Adv. Comput. Sci. Appl., vol. 10, no. 6, pp. 608–617, 2019, doi: 10.14569/ijacsa.2019.0100678. [23] N. Shrestha and F. Nasoz, “Deep Learning Sentiment Analysis of Amazon.Com Reviews and Ratings,” Int. J. Soft Comput. Artif. Intell. Appl., vol. 8, no. 1, pp. 01–15, 2019, doi: 10.5121/ijscai.2019.8101. [24] R. S. Jagdale, V. S. Shirsat, and S. N. Deshmukh, Sentiment analysis on product reviews using machine learning techniques, vol. 768, no. January. Springer Singapore, 2019. doi: 10.1007/978-981-13-0617-4_61. [25] P. Pankaj, P. Pandey, M. Muskan, and N. Soni, “Sentiment Analysis on Customer Feedback Data: Amazon Product Reviews,” Proc. Int. Conf. Mach. Learn. Big Data, Cloud Parallel Comput. Trends, Prespectives Prospect. Com. 2019, pp. 320–322, 2019, doi: 10.1109/COMITCon.2019.8862258. [26] A. Mukherjee, S. Mukhopadhyay, P. K. Panigrahi, and S. Goswami, “Utilization of Oversampling for multiclass sentiment analysis on Amazon Review Dataset,” 2019 IEEE 10th Int. Conf. Aware. Sci. Technol. iCAST 2019 - Proc., no. December, pp. 1–6, 2019, doi: 10.1109/ICAwST.2019.8923260. [27] C. Prabhavathi, P. S. Reddy, N. Vishali, and J. V Chandramouli, “Machine Learning Model for Classifying L\\_Text Using Nlp (Amazon Product Reviews),” Int. Res. J. Comput. Sci. Comput. Sci., vol. VI, no. 04, pp. 161–178, 2019, [Online]. Available: www.irjcs.com [28] T. Karthikayini and N. K. Srinath, “Comparative Polarity Analysis on Amazon Product Reviews Using Existing Machine Learning Algorithms,” 2nd Int. Conf. Comput. Syst. Inf. Technol. Sustain. Solut. CSITSS 2017, no. December 2017, pp. 1–6, 2018, doi: 10.1109/CSITSS.2017.8447660. [29] A. Veluchamy, H. Nguyen, M. L. Diop, and R. Iqbal, “Comparative Study of Sentiment Analysis with Product Reviews Using Machine Learning and Lexicon-Based Approaches,” SMU Data Sci. Rev., vol. 1, no. 4, pp. 1–22, 2018, [Online]. Available: https://scholar.smu.edu/cgi/viewcontent.cgi?article=1051&context=datasciencereview [30] K. S. Srujan, S. S. Nikhil, H. Raghav Rao, K. Karthik, B. S. Harish, and H. M. Keerthi Kumar, Classification of amazon book reviews based on sentiment analysis, vol. 672, no. January. Springer Singapore, 2018. doi: 10.1007/978-981-10-7512-4_40. [31] W. Tan, X. Wang, and X. Xu, “Sentiment Analysis for Amazon Reviews,” pp. 3–7, 2018, [Online]. Available: https://www.kaggle.com/datafiniti/consumer-reviews-of-amazon- [32] T. U. Haque, N. N. Saber, and F. M. Shah, “Sentiment analysis on large scale Amazon product reviews,” 2018 IEEE Int. Conf. Innov. Res. Dev. ICIRD 2018, no. June, pp. 1–6, 2018, doi: 10.1109/ICIRD.2018.8376299. [33] C. Pujari, Aiswarya, and N. P. Shetty, “Comparison of classification techniques for feature oriented sentiment analysis of product review data,” Adv. Intell. Syst. Comput., vol. 542, no. November, pp. 149–158, 2018, doi: 10.1007/978-981-10-3223-3_14. [34] T. U. Haque, N. N. Saber, and F. M. Shah, “Sentiment analysis on large scale Amazon product reviews,” 2018 IEEE Int. Conf. Innov. Res. Dev. ICIRD 2018, no. June 2019, pp. 1–6, 2018, doi: 10.1109/ICIRD.2018.8376299. [35] S. M. maran and P. S. esh, “Text Analysis for Product Reviews for Sentiment Analysis using NLP Methods,” Int. J. Eng. Trends Technol., vol. 47, no. 8, pp. 474–480, 2017, doi: 10.14445/22315381/ijett-v47p278. [36] C. Chauhan and S. Sehgal, “Sentiment analysis on product reviews,” Proceeding - IEEE Int. Conf. Comput. Commun. Autom. ICCCA 2017, vol. 2017-Janua, pp. 26–31, 2017, doi: 10.1109/CCAA.2017.8229825. [37] E. Tyagi and A. K. Sharma, “Sentiment Analysis of Product Reviews using Support Vector Machine Learning Algorithm,” Indian J. Sci. Technol., vol. 10, no. 35, pp. 1–9, 2017, doi: 10.17485/ijst/2017/v10i35/118965. [38] C. Sindhu, D. V. Vyas, and K. Pradyoth, “Sentiment analysis based product rating using textual reviews,” Proc. Int. Conf. Electron. Commun. Aerosp. Technol. ICECA 2017, vol. 2017-Janua, no. October, pp. 427–731, 2017, doi: 10.1109/ICECA.2017.8212762. [39] S. M. maran and P. S. esh, “Text Analysis for Product Reviews for Sentiment Analysis using NLP Methods,” Int. J. Eng. Trends Technol., vol. 47, no. 8, pp. 474–480, 2017, doi: 10.14445/22315381/ijett-v47p278. [40] L. Dey, S. Chakraborty, A. Biswas, B. Bose, and S. Tiwari, “Sentiment Analysis of Review Datasets Using Naïve Bayes‘ and K-NN Classifier,” Int. J. Inf. Eng. Electron. Bus., vol. 8, no. 4, pp. 54–62, 2016, doi: 10.5815/ijieeb.2016.04.07.

Copyright

Copyright © 2025 Ashish Mathur, Dr. Pharindara Kumar Sharma. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.