E-TİCARET PLATFORMLARININ ÇOK KRİTERLİ PERFORMANS DEĞERLENDİRMESİ: DUYGU ANALİZİ VE ENTROPY-TOPSIS ENTEGRASYONUYLA VERİ ODAKLI BİR YAKLAŞIM

Abstract

Bu çalışma, Türkiye e-ticaret pazarındaki üç büyük platformun (Trendyol, Amazon Türkiye ve Hepsiburada) çok kriterli performans değerlendirmesini objektif veriler kullanarak gerçekleştirmeyi amaçlamaktadır. Araştırmada 730 müşteri yorumu web kazıma teknikleriyle toplanmış, ön işleme sonrasında 344 temiz yoruma Türkçe sözlük tabanlı duygu analizi uygulanmıştır. Google PageSpeed, Play Store ve Şikayetvar.com verileri entegre edilerek Entropy yöntemiyle kriter ağırlıkları belirlenmiş, TOPSIS ile platformlar sıralanmıştır. Şikâyet yönetimi %77,7 ağırlıkla en belirleyici faktör olarak tespit edilmiştir. Hepsiburada %97,03, Amazon %10,00, Trendyol %2,96 yakınlık katsayısı elde etmiştir. Duyarlılık analizi, sonuçların farklı ağırlık senaryolarında tutarlı olduğunu göstermiştir. E-ticaret platformlarında şikâyet yönetimi, müşteri memnuniyetinin ve platform tercihinin kritik belirleyicisidir. Çalışma, duygu analizi ile çok kriterli karar verme yöntemlerinin entegrasyonuyla literatüre metodolojik katkı sağlamaktadır.

Keywords

• E-ticaret
• Duygu Analizi
• TOPSIS
• Entropy
• Çok Kriterli Karar Verme
• Şikâyet Yönetimi

MULTI-CRITERIA PERFORMANCE EVALUATION OF E-COMMERCE PLATFORMS: A DATA-DRIVEN APPROACH INTEGRATING SENTIMENT ANALYSIS AND ENTROPY-TOPSIS

Abstract

This study aims to conduct a multi-criteria performance evaluation of three major e-commerce platforms (Trendyol, Amazon Türkiye, and Hepsiburada) in the Turkish market using objective data. A total of 730 customer reviews were collected through web scraping techniques, and Turkish dictionary-based sentiment analysis was applied to 344 cleaned reviews after preprocessing. Data from Google PageSpeed, Play Store, and Şikayetvar.com were integrated, criterion weights were determined using the Entropy method, and platforms were ranked using TOPSIS. Complaint management was identified as the most decisive factor with 77.7% weight. Hepsiburada achieved a closeness coefficient of 97.03%, Amazon 10.00% and Trendyol 2.96%. Sensitivity analysis demonstrated that the results remained consistent across different weight scenarios. Complaint management is a critical determinant of customer satisfaction and platform preference in e-commerce. This study contributes methodologically to the literature through the integration of sentiment analysis and multi-criteria decision-making methods.

Keywords

• E-commerce
• Sentiment Analysis
• TOPSIS
• Entropy
• Multi-Criteria Decision Making
• Complaint Management

References

1. Acikalin, U. U., Bardak, B., ve Kutlu, M. (2020). Turkish Sentiment Analysis Using BERT. 2020 28th Signal Processing and Communications Applications Conference (SIU), 1–4. https://doi.org/10.1109/SIU49456.2020.9302492
2. Akın, A. A., ve Akın, M. D. (2007). Zemberek, an open source NLP framework for Turkic Languages. Structure, 10, 1–5.
3. Aydın, S., ve Kahraman, C. (2012). Evaluation of e-commerce website quality using fuzzy multi-criteria decision making approach. IAENG International Journal of Computer Science, 39. https://www.iaeng.org/IJCS/issues_v39/issue_1/IJCS_39_1_07.pdf
4. Belouaar, H., Kazar, O., Zouai, M., ve Merizig, A. (2022). A new ranking approach for E-commerce websites based on fuzzy TOPSIS algorithm. Bulletin of Electrical Engineering and Informatics, 11(2), 936–946. https://doi.org/10.11591/eei.v11i2.3563
5. Bilgihan, A., Kandampully, J., ve Zhang, T. (Christina). (2016). Towards a unified customer experience in online shopping environments. International Journal of Quality and Service Sciences, 8(1), 102–119. https://doi.org/10.1108/IJQSS-07-2015-0054
6. Büyüközkan, G., ve Çifçi, G. (2012). A combined fuzzy AHP and fuzzy TOPSIS based strategic analysis of electronic service quality in healthcare industry. Expert Systems with Applications, 39(3), 2341–2354. https://doi.org/10.1016/j.eswa.2011.08.061
7. Chevalier, J. A., ve Mayzlin, D. (2006). The Effect of Word of Mouth on Sales: Online Book Reviews. Journal of Marketing Research, 43(3), 345–354. https://doi.org/10.1509/jmkr.43.3.345
8. Dehkharghani, R., Saygin, Y., Yanikoglu, B., ve Oflazer, K. (2016). SentiTurkNet: a Turkish polarity lexicon for sentiment analysis. Language Resources and Evaluation, 50(3), 667–685. https://doi.org/10.1007/s10579-015-9307-6

9. Devlin, J., Chang, M.-W., Lee, K., ve Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. Proceedings of the 2019 Conference of the North, 4171–4186. https://doi.org/10.18653/v1/N19-1423
10. Ekin, E., ve Cesur, İ. G. (2022). Entropi Tabanlı TOPSIS VE VIKOR Yöntemleri İle Bankaların Finansal Performanslarının Değerlendirilmesine İlişkin Bir Uygulama. Journal of Turkish Operations Management, 6(2), 1327–1344. https://doi.org/10.56554/jtom.1089989
11. Galletta, D., Henry, R., McCoy, S., ve Polak, P. (2004). Web Site Delays: How Tolerant are Users? Journal of the Association for Information Systems, 5(1), 1–28. https://doi.org/10.17705/1jais.00044
12. Gezici, G., ve Yanıkoğlu, B. (2018). Sentiment Analysis in Turkish (pp. 255–271). https://doi.org/10.1007/978-3-319-90165-7_12
13. Ghorabaee, M. K., Zavadskas, E. K., Amiri, M., ve Turskis, Z. (2016). Extended EDAS Method for Fuzzy Multi-criteria Decision-making: An Application to Supplier Selection. International Journal of Computers Communications ve Control, 11(3), 358. https://doi.org/10.15837/ijccc.2016.3.2557
14. Harunasir, M. F. bin, Palanichamy, N., Haw, S.-C., ve Ng, K.-W. (2023). Sentiment Analysis of Amazon Product Reviews by Supervised Machine Learning Models. Journal of Advances in Information Technology, 14(4), 857–862. https://doi.org/10.12720/jait.14.4.857-862
15. Hwang, C.-L., ve Yoon, K. (1981). Multiple Attribute Decision Making: Methods and Applications A State-of-the-Art Survey. Springer-Verlag.
16. Kang, D., Jang, W., ve Park, Y. (2016). Evaluation of e-commerce websites using fuzzy hierarchical TOPSIS based on E-S-QUAL. Applied Soft Computing, 42, 53–65. https://doi.org/10.1016/j.asoc.2016.01.017
17. Köksalan, M., Wallenius, J., ve Zionts, S. (2011). Multiple Criteria Decision Making. WORLD SCIENTIFIC. https://doi.org/10.1142/8042
18. Kumar, A., Dash, M. K., ve Seharawat, R. (2017). Using entropy and AHP-TOPSIS for comprehensive evaluation of internet shopping malls and solution optimality. International Journal of Business Excellence, 11(4), 487. https://doi.org/10.1504/IJBEX.2017.082575
19. Laudon, K. C., ve Traver, C. G. (2021). E-Commerce 2021: Business, Technology, and Society (16th ed.). Pearson. Liu, B. (2012). Sentiment Analysis and Opinion Mining. Springer International Publishing. https://doi.org/10.1007/978-3-031-02145-9
20. Liu, Y., Lu, J., Yang, J., ve Mao, F. (2020). Sentiment analysis for e-commerce product reviews by deep learning model of Bert-BiGRU-Softmax. Mathematical Biosciences and Engineering, 17(6), 7819–7837. https://doi.org/10.3934/mbe.2020398
21. Malhotra, N. K. (2019). Marketing Research: An Applied Orientation (7th ed.). Pearson.
22. McCollough, M. A., ve Bharadwaj, S. G. (1992). The Recovery Paradox: An Examination of Consumer Satisfaction in Relation to Disconfirmation, Service Quality, and Attribution Based Theories. Marketing Theory and Applications, 119.
23. Medhat, W., Hassan, A., ve Korashy, H. (2014). Sentiment analysis algorithms and applications: A survey. Ain Shams Engineering Journal, 5(4), 1093–1113. https://doi.org/10.1016/j.asej.2014.04.011
24. Meral, M., ve Diri, B. (2014). Sentiment analysis on Twitter: Twitter üzerinde duygu analizi. 2014 22nd Signal Processing and Communications Applications Conference (SIU). https://doi.org/10.1109/SIU.2014.6830323
25. Paksoy, S. (2017a). A DEMATEL Method for Identifying Critical Success Factors in an Implementation of Information System Project. Eurasian Econometrics Statistics ve Emprical Economics Journal, 1–17. https://doi.org/10.17740/eas.stat.2017-V6-01
26. Paksoy, S. (2017b). Çok kriterli karar vermede güncel yaklaşımlar. Karahan Kitabevi.
27. Paksoy, S. (2019). TÜRKİYE’NİN İKLİM AKSİYONUNUN BUGÜNKÜ DURUMU. Çukurova Üniversitesi Sosyal Bilimler Enstitüsü Dergisi, 28(3), 155–169. https://doi.org/10.35379/cusosbil.643246
28. Pang, B., ve Lee, L. (2008). Opinion Mining and Sentiment Analysis. Foundations and Trends® in Information Retrieval, 2(1–2), 1–135. https://doi.org/10.1561/1500000011
29. Parker, G. G., Alstyne, M. W. van, ve Choudary, S. P. (2016). Platform Revolution: How Networked Markets Are Transforming the Economy. W. W. Norton ve Company.
30. Rochet, J.-C., ve Tirole, J. (2003). Platform Competition in Two-Sided Markets. Journal of the European Economic Association, 1(4), 990–1029. https://doi.org/10.1162/154247603322493212
31. Schweter, S. (2020). BERTurk-BERT models for Turkish. Zenodo. https://doi.org/10.5281/zenodo.3770924
32. Shannon, C. E. (1948). A Mathematical Theory of Communication. Bell System Technical Journal, 27(3), 379–423. https://doi.org/10.1002/j.1538-7305.1948.tb01338.x
33. Singh, J. (1988). Consumer Complaint Intentions and Behavior: Definitional and Taxonomical Issues. Journal of Marketing, 52(1), 93–107. https://doi.org/10.1177/002224298805200108
34. Singh, U., Saraswat, A., Azad, H. K., Abhishek, K., ve Shitharth, S. (2022). Towards improving e-commerce customer review analysis for sentiment detection. Scientific Reports, 12(1), 21983. https://doi.org/10.1038/s41598-022-26432-3
35. Sparks, B. A., ve Browning, V. (2011). The impact of online reviews on hotel booking intentions and perception of trust. Tourism Management, 32(6), 1310–1323. https://doi.org/10.1016/j.tourman.2010.12.011
36. Statista. (2024). Retail e-commerce sales worldwide from 2014 to 2027. https://www.statista.com/statistics/311357/sales-of-e-commerce-worldwide-by-region/?srsltid=AfmBOoqrM1kzXSSeKwi1LRyt2umZz7W4KU2Q-adiZ1PLasL_54yhhjAY
37. Sun, C.-C., ve Lin, G. T. R. (2009). Using fuzzy TOPSIS method for evaluating the competitive advantages of shopping websites. Expert Systems with Applications, 36(9), 11764–11771. https://doi.org/10.1016/j.eswa.2009.04.017
38. Taboada, M., Brooke, J., Tofiloski, M., Voll, K., ve Stede, M. (2011). Lexicon-Based Methods for Sentiment Analysis. Computational Linguistics, 37(2), 267–307. https://doi.org/10.1162/COLI_a_00049
39. Tax, S. S., Brown, S. W., ve Chandrashekaran, M. (1998). Customer Evaluations of Service Complaint Experiences: Implications for Relationship Marketing. Journal of Marketing, 62(2), 60. https://doi.org/10.2307/1252161
40. Ticaret Bakanlığı. (2025). Türkiye’de E-Ticaretin Görünümü Raporu. https://ticaret.gov.tr
41. Topaloğlu Paksoy, S., ve Karamat, R. (2025). A comparative analysis of the affordability of healthy diets across Türkiye and BRICS countries Using CoCoSo and MARCOS methods. Tarım Ekonomisi Dergisi, 31(2), 419–431. https://doi.org/10.24181/tarekoder.1732007
42. Turban, E., Outland, J., King, D., Lee, J. K., Liang, T. P. ve Turban, D. C. (2018). Electronic Commerce 2018: A Managerial and Social Networks Perspective (9th ed.). Springer.
43. Türkmenoğlu, C., ve Tantuğ, A. C. (2014). Sentiment analysis in Turkish media. Workshop on Issues of Sentiment Discovery and Opinion Mining (WISDOM’14), International Conference on Machine Learning (ICML).
44. Verhoef, P. C., Lemon, K. N., Parasuraman, A., Roggeveen, A., Tsiros, M., ve Schlesinger, L. A. (2009). Customer Experience Creation: Determinants, Dynamics and Management Strategies. Journal of Retailing, 85(1), 31–41. https://doi.org/10.1016/j.jretai.2008.11.001
45. Wang, T.-C., Thu Nguyen, T. T., ve Phan, B. N. (2022). Analyzing higher education performance by entropy - TOPSIS method: A case study in Viet Nam private universities. Measurement and Control, 55(5–6), 385–410. https://doi.org/10.1177/00202940221089504
46. Zadeh, L. A. (1965). Fuzzy sets. Information and Control, 8(3), 338–353. https://doi.org/10.1016/S0019-9958(65)90241-X