Düşük Puanlı Uygulama Yorumlarında Özellik Bazında Görüş Birliği Değerlendirmesi için Büyük Grupla Karar Alma

Öz

Tüketiciden tüketiciye (C2C) e-ticaret platformları, kullanıcıların ikinci el ürünleri alıp satmasına olanak tanımaktadır ve bu sayede kullanıcılara uygun fiyatlı alışveriş imkânı suna ve sürdürülebilir tüketime katkı sağlamaktadır. Kullanıcılar tarafından oluşturulan yorumlar ile bu platformlarda ortaya çıkan hizmet aksaklıklarını ortaya çıkarmak mümkündür. Geleneksel duygu analizi ve Hedefe Dayalı Duygu Analizi (ABSA) yöntemleri, genellikle yorumlardaki ifadelerin olumlu, olumsuz ya da nötr şeklindeki gruplandırılmasına odaklanmaktadır. Ancak bu yaklaşımlar, kullanıcılar arasındaki fikir birliğini yakalamakta ya da belirli şikâyetlerin ne kadar yaygın olduğunu tespit etmede yetersiz kalabilmektedir. Bu çalışma, ikinci el bir e-ticaret uygulamasından alınan düşük puanlı Türkçe yorumları analiz etmek için Büyük Grup Karar Verme (Large Group Decision Making - LGDM) uygulamaktadır. Bu yaklaşım, ABSA ve anlamsal benzerlik modellemesini entegre ederek kullanıcı şikâyetlerinin yorumlanabilirliğini artırmayı amaçlamaktadır. Ayrıca, yaygın şekilde paylaşılan ya da ayrışan şikâyetleri tespit edebilmekte ve geleneksel duygu toplulaştırma yöntemlerine kıyasla daha uygulanabilir içgörüler sunmaktadır.

Anahtar Kelimeler

• Büyük Grup Karar Verme
• Hedef Tabanlı Duygu Analizi
• Cümle Vektörü
• Kosinüs Benzerliği
• Online Yorumlar

Large Group Decision Making for Aspect-Level Consensus Evaluation in Low-Rated App Reviews

Öz

Consumer to consumer (C2C) e-commerce platforms allow users to buy and sell second hand products and they offer affordability and support sustainable consumption. In these environments, user generated reviews provide valuable insights into service failures. Traditional sentiment analysis and Aspect Based Sentiment Analysis (ABSA) methods primarily focus on classifying the polarity of opinions expressed in reviews. However, these approaches often fall short in capturing the user agreement or identifying whether specific complaints are widely shared. The present study adopts a Large Group Decision Making framework to analyze low rated Turkish language reviews from a second hand marketplace app. The approach integrates ABSA and semantic similarity modeling to improve the interpretability of user complaints. Also it enables to detect widely shared and divergent complaints and also offers more actionable insights than traditional sentiment aggregation.

Anahtar Kelimeler

• Large Group Consensus
• Aspect Based Sentiment Analysis
• Sentence Embedding
• Cosine Similarity
• Online Reviews

Kaynakça

1. A. Dimoka, Y. Hong, and P. A. Pavlou, "On product uncertainty in online markets: Theory and evidence," MIS Q., vol. 36, no. 2, pp. 395–426, 2012.
2. N. Hajli, "The impact of positive valence and negative valence on social commerce purchase intention," Inf. Technol. People, vol. 33, no. 2, pp. 774–791, 2020.
3. X. Yuan, T. Xu, S. He, and C. Zhang, “An online review data-driven fuzzy large-scale group decision-making method based on dual fine-tuning,” Electronics, vol. 13, no. 14, p. 2702, 2024.
4. S. P. Ladella, S. Joginpally, and K. N. Ranjit, "Aspect-Based Sentiment Analysis for Online Products," Journal of Marketing Development & Competitiveness, vol. 18, no. 4, 2024.
5. H. Baek, J. Ahn, and Y. Choi, “Helpfulness of online consumer reviews: Readers' objectives and review cues,” Int. J. Electron. Commer., vol. 17, no. 2, pp. 99–126, 2012.
6. O. A. El-Said, “Impact of online reviews on hotel booking intention: The moderating role of brand image, star category, and price,” Tour. Manag. Perspect., vol. 33, p. 100604, 2020.
7. N. Reimers and I. Gurevych, “Sentence-BERT: Sentence embeddings using siamese BERT-networks,” arXiv preprint arXiv:1908.10084, 2019.
8. I. P. Carrascosa, Large Group Decision Making: Creating Decision Support Approaches at Scale. Cham, Switzerland: Springer, 2018.

9. F. Ji, Q. Cao, H. Li, H. Fujita, C. Liang, and J. Wu, “An online reviews-driven large-scale group decision making approach for evaluating user satisfaction of sharing accommodation,” Expert Syst. Appl., vol. 213, p. 118875, 2023, doi: 10.1016/j.eswa.2022.118875.
10. X. Wu, H. Liao, and M. Tang, “Product ranking through fusing the wisdom of consumers extracted from online reviews on multiple platforms,” Knowl.-Based Syst., vol. 284, p. 111275, 2024.
11. W. Ma, F. Ji, C. Liang, Q. Sun, and J. Wu, “A deep learning and large group consensus based cruise satisfaction evaluation model with online reviews,” Inf. Sci., vol. 676, p. 120801, 2024.
12. J. Shi, Y. Zhang, H. Liu, and M. Chen, “Evaluating cruise user satisfaction through online reviews: A method based on sentiment analysis and large-scale group decision-making,” Appl. Intell., vol. 55, no. 6, pp. 418–432, 2025.
13. G. Salton and C. Buckley, “Term-weighting approaches in automatic text retrieval,” Inf. Process. Manag., vol. 24, no. 5, pp. 513–523, 1988.
14. R. Kiros, Y. Zhu, R. R. Salakhutdinov, R. Zemel, R. Urtasun, A. Torralba, and S. Fidler, “Skip-thought vectors,” in Adv. Neural Inf. Process. Syst., vol. 28, 2015.
15. A. Conneau, D. Kiela, H. Schwenk, L. Barrault, and A. Bordes, “Supervised learning of universal sentence representations from natural language inference data,” arXiv preprint arXiv:1705.02364, 2017.
16. J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of deep bidirectional transformers for language understanding,” in Proc. Conf. North Am. Chapter Assoc. Comput. Linguist.: Hum. Lang. Technol., vol. 1, pp. 4171–4186, Jun. 2019.
17. T. Gao, X. Yao, and D. Chen, “SimCSE: Simple contrastive learning of sentence embeddings,” arXiv preprint arXiv:2104.08821, 2021.
18. P. Sircar, A. Chakrabarti, D. Gupta, and A. Majumdar, “Distantly supervised aspect clustering and naming for e-commerce reviews,” in Proc. Conf. North Am. Chapter Assoc. Comput. Linguist.: Hum. Lang. Technol. - Ind. Track, pp. 94–102, 2022.
19. R. Saha, “Influence of various text embeddings on clustering performance in NLP,” arXiv preprint arXiv:2305.03144, 2023.
20. Y. J. Zhou, M. Zhou, J. B. Yang, B. Y. Cheng, and J. Wu, “Decentralized multipartite consensus model for multi-attribute group decision making: A user experience-oriented perspective,” Expert Syst. Appl., p. 127917, 2025.
21. I. UI Haq, M. Pifarré, and E. Fraca, “Novelty evaluation using sentence embedding models in open-ended cocreative problem-solving,” Int. J. Artif. Intell. Educ., pp. 1–28, 2024.
22. S. Jin and M. Tsujimoto, “Towards trust building and sustainability on second-hand platforms: A study of Mercari in Japan,” Journal of Cleaner Production, vol. 503, Art. no. 145237, 2025.
23. P. Fors, A. Nuur, and F. Randia, “Conceptualising the peer-to-peer second-hand practice-as-entity,” Cleaner and Responsible Consumption, vol. 9, p. 100119, 2023.
24. Y. Ortakci and B. Borhan, “Optimizing SBERT for long text clustering: two novel approaches with empirical insights,” The Journal of Supercomputing, vol. 81, no. 8, p. 950, 2025.
25. A. A. Akın and M. D. Akın, "Zemberek, an open source NLP framework for Turkic languages," in Proc. 3rd Int. Balkan Conf. Commun. Netw. (BalkanCom), Istanbul, Turkey, 2007.
26. E. Bigne, C. Ruiz, C. Perez-Cabañero, and A. Cuenca, "Are customer star ratings and sentiments aligned? A deep learning study of the customer service experience in tourism destinations," Service Business, vol. 17, no. 1, pp. 281–314, 2023.
27. D. García-Zamora, E. Herrera-Viedma, F. J. Cabrerizo, J. Liu, and W. Pedrycz, “Large-scale group decision making: A systematic review and a critical analysis,” IEEE/CAA Journal of Automatica Sinica, vol. 9, no. 6, pp. 949–966, Jun. 2022.