SavedAdd your journal

Journals / Afyon Kocatepe Üniversitesi Fen ve Mühendislik Bilimleri Dergisi / 2026 / Cilt: 25 Sayı: 3

BERTurk-Based Sentiment Analysis on E-Commerce Multi Domain Product Reviews

Çok Alanlı E-Ticaret Ürün İncelemelerinde BERTurk Tabanlı Duygu Analizi

Bekir Teke(ERZURUM TECHNICAL UNIVERSITY)0009-0000-3429-5845
Seda Nur Yazıcı(ERZURUM TECHNICAL UNIVERSITY)0009-0005-1160-2618
Gülseren Zamir(ERZURUM TECHNICAL UNIVERSITY)0009-0004-1405-2298
Ali Buğrahan Budak(ERZURUM TECHNICAL UNIVERSITY)0009-0001-2641-0468
Işıl Karabey Aksakallı(ERZURUM TECHNICAL UNIVERSITY)0000-0002-4156-9098
Pages
497–509
Publication Date
2025-06-10
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

As a result of the experiments, among the traditional machine learning models, Support Vector Machines (SVM) achieved the highest accuracy rate with 88%, while the BERT model was determined as the most successful model with an accuracy rate of 95%.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Product reviews on e-commerce platforms constitute an important source of information for customers' shopping processes.
📊
Key Findings & Data:In order for sellers to make strategic decisions about their products, customer satisfaction and product feedback should be analyzed in detail.
💡
Conclusion & Impact:As a result of the experiments, among the traditional machine learning models, Support Vector Machines (SVM) achieved the highest accuracy rate with 88%, while the BERT model was determined as the most successful model with an accuracy rate of 95%.
🔬Design:Review & Systematic Survey
📍Scope:Comprehensive Sample
⚙️Variables:Doğal dil işleme · Duygu analizi · Makine öğrenmesi

Abstract

Product reviews on e-commerce platforms constitute an important source of information for customers' shopping processes. Learning about the various features of products and evaluating user experiences makes shopping more reliable and provides sellers with valuable feedback on customer satisfaction. In order for sellers to make strategic decisions about their products, customer satisfaction and product feedback should be analyzed in detail. For this purpose, sentiment analysis methods are applied on the data to analyze the sentiment of the comments. In our study, sentiment analysis was performed using comments from the Trendyol e-commerce site. Our dataset was studied on a total of 73.398 data by extracting data from six different categories, namely Computer, Phone, Shoes, Clothing, Cosmetics, Sports and Outdoors, via Selenium. This dataset was divided into 80% training data and 20% test data.. The training set was validated with the fold cross-validation method. As a result of the experiments, among the traditional machine learning models, Support Vector Machines (SVM) achieved the highest accuracy rate with 88%, while the BERT model was determined as the most successful model with an accuracy rate of 95%.

Özet

E-ticaret platformlarındaki ürün yorumları, müşterilerin alışveriş süreçlerinde önemli bir bilgi kaynağı oluşturmaktadır. Ürünlerin çeşitli özellikleri hakkında bilgi edinmek ve kullanıcı deneyimlerini değerlendirmek, alışverişi daha güvenilir hale getirirken satıcılara da müşteri memnuniyeti konusunda değerli geri bildirimler sağlar. Satıcıların ürünleriyle ilgili stratejik kararlar alabilmesi için müşteri memnuniyeti ve ürünle ilgili geri bildirimlerin ayrıntılı bir şekilde analiz edilmesi gerekmektedir. Bu amaçla, yorumların duygu durumunu analiz etmek için veriler üzerinde duygu analizi yöntemleri uygulanmaktadır. Çalışmamızda, Trendyol e-ticaret sitesinin yorumları kullanılarak duygu analizi yapılmıştır. Veri setimiz, Selenium aracılığıyla Bilgisayar, Telefon, Ayakkabı, Giyim, Kozmetik, Spor ve Açık Hava olmak üzere altı farklı kategoriden veri çekilerek toplamda 73,398 veri üzerinde çalışılmıştır. Bu veri setinin %20'si test ve %80'i ise eğitim verisi olarak ayrılmıştır. Eğitim kümesi ise katlamalı çapraz doğrulama yöntemi ile doğrulanmıştır. Yapılan deneyler sonucunda geleneksel makine öğrenmesi modellerinden, en yüksek doğruluk oranını %88 ile Destek Vektör Makineleri (SVM) elde ederken, BERT modeli %95 doğruluk oranıyla en başarılı model olarak belirlenmiştir.

🔖

Cite This Article

Teke, B., Yazıcı, S. N., Zamir, G., Budak, A. B., Aksakallı, I. K. (2025). BERTurk-Based Sentiment Analysis on E-Commerce Multi Domain Product Reviews. Afyon Kocatepe Üniversitesi Fen ve Mühendislik Bilimleri Dergisi, Cilt: 25 Sayı: 3, 497–509. https://doi.org/10.35414/akufemubid.1537513

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (30)

  1. Ahmed, Z., and Wang, J., 2023. A fine-grained deep learning model using embedded-CNN with BiLSTM for exploiting product sentiments. Alexandria Engineering Journal, 65, 731-747. https://doi.org/10.1016/j.aej.2022.10.037
  2. Alaparthi, S., and Mishra, M., 2021. BERT: A sentiment analysis odyssey. Journal of Marketing Analytics, 9, 2, 118- 126. https://doi.org/10.1057/s41270-021-00109-8
  3. Amirhosseini, M. H., and Kazemian, H., 2019. Automating the process of identifying the preferred representational system in Neuro Linguistic Programming using Natural Language Processing. Cognitive processing, 20, 2, 175-193. https://doi.org/10.1007/s10339-019-00912-3
  4. Anvar Shathik, J., and Krishna Prasad, K., 2020. A literature review on application of sentiment analysis using machine learning techniques. Int J Appl Eng Manag Lett (IJAEML), 4, 2, 41-67. http://doi.org/10.5281/zenodo.3977576
  5. Baubonienė, Ž., and Gulevičiūtė, G., 2015. E-commerce factors influencing consumers ‘online shopping decision. https://doi.org/10.13165/ST-15-5-1-06
  6. Gundecha, U., 2015. Selenium Testing Tools Cookbook. Packt Publishing Ltd. Birmingham, UK, 33-48 Jones, S. C., Knotts, T. L., and Udell, G. G., 2008. Market orientation for small manufacturing suppliers: The importance of product‐related factors. Journal of Business & Industrial Marketing, 23, 7, 443-453. https://doi.org/10.1108/08858620810901202
  7. Karabila, I., Darraz, N., El-Ansari, A., Alami, N., & El Mallahi, M., 2023. Enhancing collaborative filtering-based recommender system using sentiment analysis. Future Internet, 15, 7, 235. https://doi.org/10.3390/fi15070235
  8. Kratzwald, B., Ilić, S., Kraus, M., Feuerriegel, S., and Prendinger, H., 2018. Deep learning for affective computing: Text-based emotion recognition in decision support. Decision support systems, 115, 24-35. https://doi.org/10.1016/j.dss.2018.09.002
  9. Kubrusly, J., and Valenotti, G. G. L., 2024. Comparison of document vectorization methods: a case study with textual data. Sigmae, 13, 1, 79-90. Lin, W. C., Tsai, C. F., Hu, Y. H., and Jhang, J. S., 2017. Clustering-based undersampling in class-imbalanced data. Information Sciences, 409, 17-26. https://doi.org/10.1016/j.ins.2017.05.008
  10. Lyu, F., and Choi, J., 2020. The forecasting sales volume and satisfaction of organic products through text mining on web customer reviews. Sustainability, 12, 11, 4383. https://doi.org/10.3390/su12114383
  11. Maalouf, M., 2011. Logistic regression in data analysis: an overview. International Journal of Data Analysis Techniques and Strategies, 3, 3, 281-299.
  12. Natekin, A., and Knoll, A., 2013. Gradient boosting machines, a tutorial. Frontiers in neurorobotics, 7, 21. https://doi.org/10.3389/fnbot.2013.00021
  13. Onan, A., 2021. Sentiment analysis on product reviews based on weighted word embeddings and deep neural networks. Concurrency and computation: Practice and experience, 33, 23, e5909. https://doi.org/10.1002/cpe.5909
  14. Peterson, L. E. J. S., 2009. K-nearest neighbor. 4, 2, 1883. CURRICULUM VITAE. https://doi.org/10.4249/scholarpedia
  15. Prottasha, N. J., Sami, A. A., Kowsher, M., Murad, S. A., Bairagi, A. K., Masud, M., and Baz, M., 2022. Transfer learning for sentiment analysis using BERT based supervised fine-tuning. Sensors, 22, 11, 4157. https://doi.org/10.3390/s22114157
  16. Rathi, M., Malik, A., Varshney, D., Sharma, R., and Mendiratta, S., 2018. Sentiment analysis of tweets using machine learning approach. In 2018 IEEE Eleventh international conference on contemporary computing (IC3), Noida, India, 1-3.
  17. Rigatti, Steven J., 2017, Random forest. Journal of Insurance Medicine. 47, 1, 31-39. https://doi.org/10.17849/insm-47-01-31-39.1
  18. Sasikala, P., and Mary Immaculate Sheela, L., 2020. Sentiment analysis of online product reviews using DLMNN and future prediction of online product using IANFIS. Journal of Big Data, 7, 1, 33. https://doi.org/10.1186/s40537-020-00308-7
  19. Shankar, A., Perumal, P., Subramanian, M., Ramu, N., Natesan, D., Kulkarni, V. R., and Stephan, T., 2024. An intelligent recommendation system in e-commerce using ensemble learning. Multimedia Tools and Applications, 83, 16, 48521-48537. https://doi.org/10.1007/s11042-023-17415-1
  20. Shariff, S. M., 2019. Investigating Selenium Usage Challenges and Reducing the Performance Overhead of Selenium-Based Load Tests, Master Thesis, Kingston, Ontario, Canada, 100
  21. Suthaharan, S., and Suthaharan, S., 2016. Support vector machine. Machine learning models and algorithms for big data classification: thinking with examples for effective learning, 207-235. https://doi.org/10.1007/978-1-4899-7641-3_9
  22. Suthaharan, S., & Suthaharan, S., 2016. Decision tree learning. Machine Learning Models and Algorithms for Big Data Classification: Thinking with Examples for Effective Learning, 237-269. https://doi.org/10.1007/978-1-4899-7641-3_10
  23. Ullah, A., Khan, K., Khan, A., and Ullah, S., 2023. Understanding quality of products from customers’ attitude using advanced machine learning methods. Computers, 12, 3, 49. https://doi.org/10.3390/computers12030049
  24. Vigneron, V., and Chen, H. 2016. A multi-scale seriation algorithm for clustering sparse imbalanced data: application to spike sorting. Pattern Analysis and Applications, 19, 885-903. https://doi.org/10.1007/s10044-015-0458-2
  25. Wang, X., Yi, G., and Wang, Y., 2021. Automated Functional Testing of Search Engines using Metamorphic Testing. In 2021 IEEE 21st International Conference on Software Quality, Reliability and Security Companion (QRS-C), Hainan, China, 22-29. https://doi.org/10.1109/QRS-C55045.2021.00014
  26. Xu, S., 2018. Bayesian Naïve Bayes classifiers to text classification. Journal of Information Science, 44, 1, 48-59. https://doi.org/10.1177/0165551516677946
  27. Zada, A. J. J., and Albayrak, A., 2023. Duygu Analizi ve Topluluk Öğrenmesi Yaklaşımları ile Kullanıcı Yorumlarının Analizi. Düzce Üniversitesi Bilim ve Teknoloji Dergisi, 11, 4, 1725-1732. https://doi.org/10.29130/dubited.1102181
  28. Zhao, H., Liu, Z., Yao, X., and Yang, Q., 2021. A machine learning-based sentiment analysis of online product reviews with a novel term weighting and feature selection approach. Information Processing & Management, 58, 5, 102656. https://doi.org/10.1016/j.ipm.2021.102656
  29. Amirhosseini, M. H., and Kazemian, H., 2019. Automating the process of identifying the preferred representational system in Neuro Linguistic Programming using Natural Language Processing. Cognitive processing, 20, 2, 175-193. https://doi.org/10.1007/s10339-019-00912-3
  30. Peterson, L. E. J. S., 2009. K-nearest neighbor. 4, 2, 1883. CURRICULUM VITAE. https://doi.org/10.4249/scholarpedia