Green Sentiment Analysis in E-Commerce Reviews: A Comparative Machine Learning Approach on Turkish Consumer Feedback

Year 2026, Volume: 9 Issue: 2, 826 - 834, 15.03.2026

Cevher Özden

https://doi.org/10.34248/bsengineering.1836772

https://izlik.org/JA65FF38AH

Abstract

This study investigates the effectiveness of three sentiment classification approaches, i.e. Logistic Regression (LR), Support Vector Classification (SVC), and a fine-tuned BERTurk model, on Turkish e-commerce reviews related to environmentally conscious, or “green,” products. Using a real-world dataset drawn from Trendyol, one of Türkiye’s largest online marketplaces, we preprocessed and filtered the data to focus on user-generated product comments that reference sustainability-oriented themes. Each model was evaluated using standard classification metrics, including accuracy and macro-averaged F1-score, to assess both overall performance and sensitivity to class imbalance. The results show that while classical machine learning methods such as LR and SVC provide reasonably high accuracy, they struggle to distinguish neutral sentiment effectively, which is an issue commonly encountered in Turkish-language sentiment tasks. In contrast, the BERTurk model achieved the highest overall performance, with an accuracy of 0.91 and a macro F1-score of 0.67. It was particularly effective in detecting positive and negative sentiment, while still exhibiting the known difficulty of identifying neutral expressions. These findings suggest that transformer-based models offer a clear advantage in extracting sentiment from morphologically rich languages like Turkish, especially in domains where emotional nuance and linguistic ambiguity are prevalent. The study contributes to both the sentiment analysis literature and Management Information Systems research by demonstrating the value of domain-specific deep learning for consumer analytics in green commerce. It highlights practical implications for businesses aiming to understand and respond to public attitudes toward sustainable products and emphasizes the need for improved modeling of neutral sentiment. Future work should focus on expanding Turkish sentiment datasets, addressing class imbalance, and refining model architectures to better capture the subtleties of eco-conscious consumer expression.

Keywords

Turkish sentiment analysis , BERTurk , Green commerce , E-commerce reviews , Transformer models

Ethical Statement

Ethics committee approval was not required for this study because there was no study on animals or humans.

Supporting Institution

The author declares that this research received no specific grant from any funding agency in the public, commercial, or not-for-profit sectors.

References

• Aguilar-Moreno, J. A., Palos-Sánchez, P. R., & Pozo-Barajas, R. (2024). Sentiment analysis to support business decision-making: A bibliometric study. AIMS Mathematics, 9, 4337–4375. https://doi.org/10.3934/math.2024215
• Bilik, M. (2023). Analyzing Challenges and Opportunities in the E-Commerce Industry of Turkey. İzmir İktisat Dergisi, 38(4), 1138-1151. https://doi.org/10.24988/ije.1262286
• Brendel, A. B., Chasin, F., Mirbabaie, M., Riehle, D. M., & Harnischmacher, C. (2022). Review of design-oriented Green Information Systems research. Sustainability, 14(8), 4650. https://doi.org/10.3390/su14084650
• Chiang, C.-T. (2024). A systematic literature network analysis of green information technology for sustainability: Toward smart and sustainable livelihoods. Technological Forecasting and Social Change, 199, 123053. https://doi.org/10.1016/j.techfore.2023.123053.
• Çubukçu-Çerasi, C. (2023). Embracing green choices: Sentiment analysis of sustainable consumption. In 2023 International Conference on Research in Engineering, Technology and Science (ICRETS) (pp. 254–255). https://dergipark.org.tr/en/download/article-file/3431062
• Daza, A., González Rueda, N. D., Aguilar Sánchez, M. S., Robles Espíritu, W. F., & Chauca Quiñones, M. E. (2024). Sentiment analysis on e-commerce product reviews using machine learning and deep learning algorithms: A bibliometric analysis, systematic literature review, challenges and future works. International Journal of Information Management Data Insights, 4(2), 100267. https://doi.org/10.1016/j.jjimei.2024.100267
• Demir, A. F. (2024). Trendyol product comments [Data set]. Kaggle. Retrieved from https://www.kaggle.com/datasets/ahmetfurkandemr/trendyol-product-comments/
• Doğan, A., & Kara, N. (2025). Sözcük Tabanlı Duygu Analizi: Sosyal Medya Paylaşımlarına Dayalı E-Ticaret Siteleri Memnuniyet Düzeyi Karşılaştırması. Osmaniye Korkut Ata Üniversitesi Fen Bilimleri Enstitüsü Dergisi, 8(4), 1624-1643. https://doi.org/10.47495/okufbed.1604591
• Gürbüz, M., & Kotan, M. (2025). Multi-category e-commerce insights via social media analysis using machine learning and BERT. Acta Infologica, 9(1), 1–18. https://doi.org/10.26650/acin.1483488
• Huang, H., Zavareh, A.A. and Mustafa, M.B. (2023) Sentiment Analysis in E-Commerce Platforms: A Review of Current Techniques and Future Directions. IEEE Access, 11, 90367-90382. https://doi.org/10.1109/access.2023.3307308
• Incidelen, M., & Aydoğan, M. (2025). Sentiment analysis in Turkish using language models: A comparative study. European Journal of Technique, 15(1), 68–74. https://doi.org/10.36222/ejt.1592448
• Loke, R. E., & Pathak, S. (2023). Decision support system for corporate reputation based on social media sentiment analysis. In Proceedings of the 18th International Conference on Evaluation of Novel Approaches to Software Engineering. https://www.scitepress.org/Papers/2023/121364/121364.pdf
• Maarif, M. R., Syafrudin, M., & Fitriyani, N. L. (2024). Uncovering Sustainability Insights from Amazon’s Eco-Friendly Product Reviews for Design Optimization. Sustainability, 16(1), 172. https://doi.org/10.3390/su16010172
• Macías Urrego, J. A., García Pineda, V., & Montoya Restrepo, L. A. (2024). The power of social media in the decision-making of current and future professionals: a crucial analysis in the digital era. Cogent Business & Management, 11(1). https://doi.org/10.1080/23311975.2024.2421411
• Mangiaracina R, Marchet G, Perotti S, Tumino A (2015), "A review of the environmental implications of B2C e-commerce: a logistics perspective". International Journal of Physical Distribution & Logistics Management, Vol. 45 No. 6 pp. 565–591, doi: https://doi.org/10.1108/IJPDLM-06-2014-0133
• Nave, M., Rita, P., & Guerreiro, J. (2018). A decision support system framework to track consumer sentiments in social media. Journal of Hospitality Marketing & Management, 27(6), 693–710. https://doi.org/10.1080/19368623.2018.1435327
• Öcal, A. (2025). BERT-based sentiment analysis of Turkish e-commerce reviews: Star ratings versus text. Sakarya University Journal of Computer and Information Sciences, 8(4), 677–687. https://doi.org/10.35377/saucis...1747068
• Oláh, J., Popp, J., Khan, M.A., & Kitukutha, N. (2022). Sustainable e-commerce and environmental impact on consumer behaviour. Economics and Sociology, 15(2), 271–285. https://doi.org/10.14254/2071-789X.2023/16-1/6
• Onan, A., & Balbal, K. F. (2024). Improving Turkish text sentiment classification through task-specific and universal transformations: An ensemble data augmentation approach. IEEE Access, 12, 4413–4458. https://doi.org/10.1109/ACCESS.2024.3349971
• Özmen, C. G., & Gündüz, S. (2025). Comparison of machine learning models for sentiment analysis of big Turkish web-based data. Applied Sciences, 15(5), 2297. https://doi.org/10.3390/app15052297
• Ramos, C. M. Q., Cardoso, P. J. S., Fernandes, H. C. L., & Rodrigues, J. M. F. (2023). A Decision-Support System to Analyse Customer Satisfaction Applied to a Tourism Transport Service. Multimodal Technologies and Interaction, 7(1), 5. https://doi.org/10.3390/mti7010005
• 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. https://doi.org/10.1016/j.jksuci.2023.02.017
• Shaik Vadla, M. K., Suresh, M. A., & Viswanathan, V. K. (2024). Enhancing Product Design through AI-Driven Sentiment Analysis of Amazon Reviews Using BERT. Algorithms, 17(2), 59. https://doi.org/10.3390/a17020059
• Singh N, Jung I, Han H, Ariza-Montes A, Vega-Muñoz A. (2022). Green Information System (GIS) Model in the Conference Sector: Exploring Attendees’ Adoption Behaviors for Conference Apps. Psychol Res Behav Manag. 2022;15:2229-2243. https://doi.org/10.2147/PRBM.S370657
• Teke, B., Yazıcı, S. N., Zamir, G., Budak, A. B., & Karabey Aksakallı, İ. (2025). BERTurk-based sentiment analysis on e-commerce multi domain product reviews. Afyon Kocatepe University Journal of Science and Engineering, 25(3), 497–509. https://doi.org/10.35414/akufemubid.1537513
• UNCTAD. (2024). E-commerce and environmental sustainability (Chapter 5). United Nations Conference on Trade and Development. https://unctad.org/system/files/official-document/der2024_ch05_en.pdf
• Wu, P., Tang, T., Zhou, L., & Martínez, L. (2024). A decision-support model through online reviews: Consumer preference analysis and product ranking. Information Processing & Management, 61(4), 103728. https://doi.org/10.1016/j.ipm.2024.103728
• Zhang, Z., Guo, J., Zhang, H. Zhou, L., & Wang, M. (2022). Product selection based on sentiment analysis of online reviews: an intuitionistic fuzzy TODIM method. Complex Intell. Syst. 8, 3349–3362 (2022). https://doi.org/10.1007/s40747-022-00678-w
• Zümberoğlu, K. B., Dik, S. Z., Karadeniz, B. S., & Sahmoud, S. (2025). Towards better sentiment analysis in the Turkish language: Dataset improvements and model innovations. Applied Sciences, 15(4), 2062. https://doi.org/10.3390/app15042062