Multi-Category E-Commerce Insights via Social Media Analysis using Machine Learning and BERT

Abstract

The burgeoning prevalence of Internet and social media usage has empowered consumers to effortlessly share their opinions about products and services on social media platforms and websites. Consequently, recent research has focused on using machine learning, text mining, and sentiment analysis techniques to extract valuable insights. These insights can then be employed to support businesses in enhancing customer satisfaction and making informed operational and strategic decisions. In this study, a dataset of 5806 Trendyol user reviews was collected from X using the X API within a specified time frame. The dataset was preprocessed and categorized into five predefined categories: product, support, logistics, advertising, and off-topic. Subsequently, the test set was classified using eight machine learning techniques and compared. Finally, sentiment analysis was performed using the pretrained BERTurk model to evaluate user satisfaction and dissatisfaction levels. By integrating machine learning and BERT, this study extracted a general assessment profile of social media users, particularly for e-commerce platforms, and examined social media perspectives on a multi-category basis.

Keywords

• Sentiment Analysis
• Machine Learning
• Transformers
• User Reviews
• E-commerce

References

1. Arobi, R., Rijon, R. H., Haque, N., Safkat, T. I. M., & Safoan, S. (2022). Sentiment analysis on E-commerce based product reviews using machine learning algorithms (Doctoral dissertation, Brac University). google scholar
2. Anjaria, M., & Guddeti, R. M. R. (2014). Influence factor based opinion mining of Twitter data using supervised learning. In 2014 sixth international conference on communication systems and networks (COMSNETS) (pp. 1-8). IEEE. google scholar
3. Bayhaqy, A., Sfenrianto, S., Nainggolan, K., & Kaburuan, E. R. (2018, October). Sentiment analysis about E-commerce from tweets using decision tree, K-nearest neighbor, and naîve baYes. İn 2018 International conference on orange Technologies (ICOT) (pp. 1-6). IEEE. google scholar
4. Chaubey, G., Gavhane, P. R., Bisen, D., & Arjaria, S. K. (2023). Customer purchasing behavior prediction using machine learning classifi-cation techniques. Journal of Ambient Intelligence and Humanized Computing, 14(12), 16133-16157. google scholar
5. Chen, N. (2022). Research on E-Commerce DataBase Marketing Based on Machine Learning ALgorithm. Computational Intelligence and Neuroscience, 2022(1), 7973446. google scholar
6. Demircan, M., Seller, A., Abut, F., & AkaY, M. F. (2021). Developing Turkish sentiment analYsis models using machine learning and e-commerce data. International Journal of Cognitive Computing in Engineering, 2, 202-207. google scholar
7. Deniz, E., ErbaY, H., & Coşar, M. (2022). Multi-label classification of e-commerce customer reviews via machine learning. Axioms, 11(9), 436. google scholar
8. Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2018). Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805. google scholar

9. Dharrao, D., Deokate, S., Bongale, A. M., & Urolagin, S. (2023, March). E-commerce product review classification based on supervised machine learning techniques. In 2023 9th International Conference on Advanced Computing and Communication Systems (ICACCS) (Vol. 1, pp. 1934-1939). IEEE. google scholar
10. George, A. S., & Baskar, T. (2024). Leveraging Big Data and Sentiment Analysis for Actionable Insights: A Review of Data Mining Approaches for Social Media. Partners Universal International Innovation Journal, 2(4), 39-59. google scholar
11. Grandi, U., Loreggia, A., Rossi, F., & Saraswat, V. (2015). A borda count for collective sentiment analysis. Annals of Mathematics and Artificial Intelligence, 77(3-4), 281-302. https://doi.org/10.1007/s10472-015-9488-0 google scholar
12. Gound, R. S., Tikone, P. V., Suryawanshi, S. S., & Nagpal, D. (2018). Twitter Data Sentiment Analysis and Visualization. International Journal of Computer Applications, 975, 8887. google scholar
13. Guven, Z. A. (2021a). The effect of bert, electra and albert language models on sentiment analysis for turkish product reviews. In 2021 6th international conference on computer science and engineering (UBMK) (pp. 629-632). IEEE. google scholar
14. Guven, Z. A. (2021b). Comparison of BERT models and machine learning methods for sentiment analysis on Turkish tweets. In 2021 6th International Conference on Computer Science and Engineering (UBMK) (pp. 98-101). IEEE. google scholar
15. Haque, T. U., Saber, N. N., & Shah, F. M. (2018, May). Sentiment analysis on large scale Amazon product reviews. In 2018 IEEE international conference on innovative research and development (ICIRD) (pp. 1-6). IEEE. google scholar
16. He, H., Zhou, G., & Zhao, S. (2022). Exploring e-commerce product experience based on fusion sentiment analysis method. IEEE Access, 10, 110248-110260. google scholar
17. Huang, H., Asemi, A., & Mustafa, M. B. (2023). Sentiment analysis in e-commerce platforms: A review of current techniques and future directions. IEEE Access. google scholar
18. Jabbar, J., Urooj, I., JunSheng, W., & Azeem, N. (2019). Real-time sentiment analysis on E-commerce application. In 2019 IEEE 16th international conference on networking, sensing and control (ICNSC) (pp. 391-396). IEEE. google scholar
19. Koksal, D., Alacan, M. M., Olgun, E., & Sakar, C. O. (2022). Natural Language Processing-Based Product Category Classification Model for E-Commerce. In 2022 30th Signal Processing and Communications Applications Conference (SIU) (pp. 1-4). IEEE. google scholar
20. Köksal, A., & Özgür, A. (2021). Twitter dataset and evaluation of transformers for Turkish sentiment analysis. In 2021 29th Signal Processing and Communications Applications Conference (SIU) (pp. 1-4). IEEE. google scholar
21. Kotan, M. (2022). Duygu Analizi ve Dijital Dönüşüm Üzerine Etkileri. In Book: Dijital Etkileşimler ve Sektörel Yansımaları II. Gazi Kitapevi. google scholar
22. Kubrusly, J., Neves, A. L., & Marques, T. L. (2022). A statistical analysis of textual e-commerce reviews using tree-based methods. Open Journal of Statistics, 12(3), 357-372. google scholar
23. Kumar, K. S., Desai, J., & Majumdar, J. (2016, December). Opinion mining and sentiment analysis on online customer review. In 2016 IEEE international conference on computational intelligence and computing research (ICCIC) (pp. 1-4). IEEE. google scholar
24. Marong, M., Batcha, N. K., & Mafas, R. (2020). Sentiment Analysis in E-Commerce: A Review on The Techniques and Algorithms. Journal of Applied Technology and Innovation, 4(1), 6. google scholar
25. Polat, H., & Ağca, Y. (2022). Tripadvisor Kullanıcılarının Türkçe Ve İngilizce Yorumları Kapsamında Duygu Analizi Yöntemlerinin Karşılaştırmalı Analizi. Abant sosyal bilimler dergisi, 22(2), 901-916. google scholar
26. Poyraz, Y. Z., Tugcu, M., & Amasyali, M. F. (2022). Improving BERT Pre-training with Hard Negative Pairs. In 2022 Innovations in Intelligent Systems and Applications Conference (ASYU) (pp. 1-6). IEEE. google scholar
27. Rumelli, M., Akkuş, D., Kart, Ö., & Isik, Z. (2019, October). Sentiment analysis in Turkish text with machine learning algorithms. In 2019 Innovations in intelligent systems and applications conference (ASYU) (pp. 1-5). IEEE. google scholar
28. Qin, Z., Dong, K., & Xie, B. (2024). What affects customers’ online shopping behavior, research that applied machine learning to Amazon product reviews. Applied and Computational Engineering, 76, 48-64. google scholar
29. Saleem, H., Muhammad, K. B., Nizamani, A. H., Saleem, S., & Aslam, A. M. (2019). Data science and machine learning approach to improve E-commerce sales performance on social web. International Journal of Computer Science and Network Security (IJCSNS), 19. google scholar
30. Savci, P., & Das, B. (2023). Prediction of the customers’ interests using sentiment analysis in e-commerce data for comparison of Arabic, English, and Turkish languages. Journal of King Saud University-Computer and Information Sciences, 35(3), 227-237. google scholar
31. Sayeed, M. S., Mohan, V., & Muthu, K. S. (2023). BERT: A Review of Applications in Sentiment Analysis. HighTech and Innovation Journal, 4(2), 453-462. google scholar
32. Schweter, S. (2020). Berturk—Bert models for turkish. Zenodo. https://doi.org/10.5281/zenodo.3770924 google scholar
33. Shanto, S. S., Ahmed, Z., & Jony, A. I. (2023). Mining User Opinions: A Balanced Bangla Sentiment Analysis Dataset for E-Commerce. Malaysian Journal of Science and Advanced Technology, 272-279. google scholar
34. Shehu, H. A., & Tokat, S. (2020). A hybrid approach for the sentiment analysis of Turkish Twitter data. In Artificial Intelligence and Applied Mathematics in Engineering Problems: Proceedings of the International Conference on Artificial Intelligence and Applied Mathematics in Engineering (ICAIAME 2019) (pp. 182-190). Springer International Publishing. google scholar
35. Şimşek, İ., Kökçam, A. H., Demir, H. I., Erden, C. (2023). Sentiment Analysis of Twitter Data of Hepsiburada E-commerce Site Customers with Natural Language Processing. In International Symposium on Intelligent Manufacturing and Service Systems (pp. 567-578). Singapore: Springer Nature Singapore. google scholar
36. Tang, D., Qin, B., Liu, T., & Yang, Y. (2015, June). User modeling with neural network for review rating prediction. In Twenty-fourth international joint conference on artificial intelligence. google scholar
37. Taşcı, M. E., Rasheed, J., & Özkul, T. (2024, January). Sentiment Analysis on Reviews of Amazon Products Using Different Machine Learning Algorithms. In International Conference on Forthcoming Networks and Sustainability in the AIoT Era (pp. 318-327). Cham: Springer Nature Switzerland. google scholar
38. Stephenie, Warsito, B., & Prahutama, A. (2020). Sentiment analysis on tokopedia product online reviews using random forest method. In E3S Web of Conferences (Vol. 202, p. 16006). EDP Sciences. google scholar
39. X Help Center. (2024). About different types of posts. Retrieved from https://help.twitter.com/en/using-x/types-of-posts google scholar
40. Xu, F., Pan, Z., & Xia, R. (2020). E-commerce product review sentiment classification based on a naıve BaYes continuous learning framework. Information Processing & Management, 57(5), 102221. google scholar
41. Yang, L., Li, Y., Wang, J., & Sherratt, R. S. (2020). Sentiment analYsis for E-commerce product reviews in Chinese based on sentiment lexicon and deep learning. IEEE Access, 8, 23522-23530. google scholar
42. Yildırım, S. (2024). Fine-tuning Transformer-based Encoder for Turkish Language Understanding Tasks. arXiv preprint arXiv:2401.17396. google scholar
43. Yıldırım, S., & Asgari-Chenaghlu, M. (2021). Mastering Transformers: Build state-of-the-art models from scratch with advanced natural language processing techniques. Packt Publishing Ltd. google scholar
44. Yıldız, H. (2020). The Role Of Machine Learning Algorithms In Determining Product Sales In E-Commerce: A Case StudY For TurkeY. Current and Historical Debates in Social Sciences: Field Studies and Analysis, 175. google scholar
45. Zada, A. J. J., & AlbaYrak, A. (2023). DuYgu Analizi ve Topluluk Öğrenmesi Yaklaşımları ile Kullanıcı Yorumlarının Analizi. Düzce Üniversitesi Bilim ve Teknoloji Dergisi, 11(4), 1725-1732. google scholar