A Calibrated Analysis of Customer Rating–Sentiment Mismatch: An Examination of eWOM Reviews of Michelin-Starred Restaurants in Istanbul

Abstract

Online customer reviews are used as a decisive source of information in restaurant choice. However, reading star ratings alone does not always reflect the emotional tone conveyed in the review text. This mismatch is thought to become more pronounced in high-end (fine-dining) restaurants, where expectations are high. By contrast, studies relying on domain-specific calibrated measures in Michelin-starred restaurants remain limited. In this study, directional rating–sentiment mismatch was examined using 5,281 multilingual Google reviews (2017–2026) of eight Michelin-starred restaurants in Istanbul. Sentiment classification was performed with a transformer-based classifier calibrated on 500 human-labeled reviews. In ordered and binary logistic regression models—controlling for review length and including restaurant and month fixed effects—text-derived sentiment was found to strongly explain star ratings. A one-step increase in sentiment was estimated to raise the odds of a five-star rating by approximately 3.35 times and to lower the odds of a one- or two-star rating to 0.18. Despite this overall alignment, negative sentiment was identified in 7.7% of five-star reviews and positive sentiment in 22.8% of one- and two-star reviews. Moreover, the mismatch rate was found to vary across restaurants. These findings indicate that monitoring based solely on star ratings may miss dissatisfaction signals concealed within high ratings. By empirically quantifying rating–sentiment mismatch through domain-specific calibrated sentiment measurement in multilingual reviews, this study contributes to this gap in the literature.

Keywords

• gastronomy tourism
• electronic word-of-mouth
• online reviews

Müşteri Puanı-Duygu Uyumsuzluğunun Kalibre Analizi: İstanbul'daki Michelin Yıldızlı Restoranların eWOM Yorumlarının İncelenmesi

Abstract

Çevrim içi müşteri yorumları, restoran seçimlerinde belirleyici bir bilgi kaynağı olarak kullanılmaktadır. Ancak yıldız puanlarının tek başına okunması, yorum metnindeki duygusal tonu her zaman yansıtmamaktadır. Bu uyumsuzluğun, beklentinin yüksek olduğu üst düzey restoranlarda daha belirgin hale geldiği düşünülmektedir. Buna karşın Michelin yıldızlı restoranlarda, alana özgü kalibre edilmiş ölçümlere dayanan çalışmalar sınırlı kalmıştır. Bu çalışmada, İstanbul'daki sekiz Michelin yıldızlı restorana ait 5.281 adet çok dilli Google yorumu (2017–2026) üzerinden yönlü puan–duygu uyumsuzluğu incelenmiştir. Duygu sınıflandırması, 500 insan etiketli yorumla kalibre edilmiş transformer tabanlı bir sınıflandırıcıyla yapılmıştır. Yorum uzunluğu ile restoran ve ay sabit etkileri kontrol edilerek kurulan sıralı ve ikili lojistik regresyon modellerinde, metinden türetilen duygunun yıldız puanlarını güçlü biçimde açıkladığı bulunmuştur. Duyguda bir basamaklık artışta, beş yıldız olasılığının yaklaşık 3,35 kat arttığı, bir–iki yıldız olasılığının ise 0,18 düzeyine düştüğü hesaplanmıştır. Genel uyuma karşın, beş yıldızlı yorumların %7,7'sinde olumsuz, bir–iki yıldızlı yorumların %22,8'inde olumlu duygu saptanmıştır. Ayrıca uyumsuzluk oranının restoranlar arasında farklılaştığı görülmüştür. Bu bulgular, yalnızca yıldız puanlarına dayalı izlemenin yüksek puanlar içinde gizlenen memnuniyetsizlik sinyallerini kaçırabileceğine işaret etmektedir. Çalışma, çok dilli yorumlarda alana özgü kalibre edilmiş duygu ölçümüyle puan–duygu uyumsuzluğunu ampirik olarak sayısallaştırarak alanyazındaki bu boşluğa katkı sunmaktadır.

Keywords

• gastronomi turizmi
• elektronik ağızdan ağıza iletişim
• Çevrimiçi değerlendirmeler
• müşteri duygu analizi

References

1. Aghakhani, N., Oh, O., Gregg, D. G. ve Karimi, J. (2021). Online review consistency matters: An elaboration likelihood model perspective. Information Systems Frontiers, 23(5), 1287–1301. https://doi.org/10.1007/s10796-020-10030-7
2. Almansour, A., Alotaibi, R. ve Alharbi, H. (2022). Text-rating review discrepancy (TRRD): An integrative review and implications for research. Future Business Journal, 8(1), 3. https://doi.org/10.1186/s43093-022-00114-y
3. Anderson, E. W. (1998). Customer satisfaction and word of mouth. Journal of Service Research, 1(1), 5–17. https://doi.org/10.1177/109467059800100102
4. Bang, D., Choi, K. ve Kim, A. J. (2022). Does Michelin effect exist? An empirical study on the effects of Michelin stars. International Journal of Contemporary Hospitality Management, 34(6), 2298–2319. https://doi.org/10.1108/IJCHM-08-2021-1025
5. Barrera-Barrera, R. (2023). Identifying the attributes of consumer experience in Michelin-starred restaurants: A text-mining analysis of online customer reviews. British Food Journal, 125(13), 579–598. https://doi.org/10.1108/BFJ-05-2023-0408
6. Baykal, M. ve Yazıcı Ayyıldız, A. (2024). İstanbul ve Londra'daki Michelin yıldızlı restoranlara yönelik müşteri şikâyetlerinin karşılaştırılması. Journal of Tourism and Gastronomy Studies, 12(2), 850–868. https://doi.org/10.21325/jotags.2024.1415
7. Bi, J.-W., Zhu, X.-E. ve Han, T.-Y. (2024). Text analysis in tourism and hospitality: A comprehensive review. Journal of Travel Research, 63(8), 1847–1869. https://doi.org/10.1177/00472875241247318
8. Bian, Z. ve Che, C. (2025). How AI overview of customer reviews influences consumer perceptions in e-commerce? Journal of Theoretical and Applied Electronic Commerce Research, 20(4), 315. https://doi.org/10.3390/jtaer20040315

9. Blitzer, J., Dredze, M. ve Pereira, F. (2007). Biographies, Bollywood, boom-boxes and blenders: Domain adaptation for sentiment classification. A. Zaenen ve A. van den Bosch (Ed.), Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics içinde (s. 440–447). Association for Computational Linguistics.
10. Chiang, C. F. ve Guo, H. W. (2021). Consumer perceptions of the Michelin Guide and attitudes toward Michelin-starred restaurants. International Journal of Hospitality Management, 93, 102793. https://doi.org/10.1016/j.ijhm.2020.102793
11. Competition and Markets Authority. (2025). Fake reviews guidance (CMA208). https://assets.publishing.service.gov.uk/media/67eeb64fe9c76fa33048c790/CMA208_-_Fake_reviews_guidance.pdf
12. Daries, N., Moreno-Gené, J. ve Cristobal-Fransi, E. (2021). Michelin stars shine brightly, but are they profitable? International Journal of Gastronomy and Food Science, 24, 100352. https://doi.org/10.1016/j.ijgfs.2021.100352
13. Demir, Y. (2025). Michelin Yeşil Yıldızı'na sahip restoranlarla ilgili müşteri deneyim ve algılamalarının analizi: Google Haritalar örneği. Iğdır Üniversitesi Sosyal Bilimler Dergisi, 14(38), 118–135. https://doi.org/10.54600/igdirsosbilder.1496079
14. Devlin, J., Chang, M.-W., Lee, K. ve Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. J. Burstein, C. Doran ve T. Solorio (Ed.), Proceedings of the 2019 Conference of the
15. North American Chapter of the Association for Computational Linguistics: Human Language Technologies içinde (Cilt 1, s. 4171–4186). Association for Computational Linguistics. https://doi.org/10.18653/v1/N19-1423
16. Greenberg, J., Sands, D. B., Cattani, G. ve Porac, J. (2024). Rating systems and increased heterogeneity in firm performance: Evidence from the New York City restaurant industry, 1994–2013. Strategic Management Journal, 45(1), 36–65. https://doi.org/10.1002/smj.3545
17. Guo, Y., Barnes, S. J. ve Jia, Q. (2017). Mining meaning from online ratings and reviews: Tourist satisfaction analysis using latent Dirichlet allocation. Tourism Management, 59, 467–483. https://doi.org/10.1016/j.tourman.2016.09.009
18. Hennig-Thurau, T., Gwinner, K. P., Walsh, G. ve Gremler, D. D. (2004). Electronic word-of-mouth via consumer-opinion platforms: What motivates consumers to articulate themselves on the Internet? Journal of Interactive Marketing, 18(1), 38–52. https://doi.org/10.1002/dir.10073
19. Hu, N., Pavlou, P. A. ve Zhang, J. (2009). Overcoming the J-shaped distribution of product reviews. Communications of the ACM, 52(10), 144–147. https://doi.org/10.1145/1562764.1562800
20. Huang, Y., Hall, C. M. ve Chen, N. (2024). Destination restaurants' practices and the production of locality: The case of Michelin restaurants in China. Foods, 13(12), 1838. https://doi.org/10.3390/foods13121838
21. Jia, S., Chi, O. H. ve Chi, C. G. (2025). Unpacking the impact of AI vs. human-generated review summary on hotel booking intentions. International Journal of Hospitality Management, 126, 104030. https://doi.org/10.1016/j.ijhm.2024.104030
22. Kiatkawsin, K. ve Sutherland, I. (2020). Examining luxury restaurant dining experience towards sustainable reputation of the Michelin restaurant guide. Sustainability, 12(5), 2134. https://doi.org/10.3390/su12052134
23. Kim, H.-S. (2025). Generation Z's Michelin choices: Survey and big data insights into Thailand's Michelin-starred restaurants. International Journal of Tourism Research, 27(5), e70135. https://doi.org/10.1002/jtr.70135
24. Kocaman, S. (2018). Turizmde elektronik ağızdan ağıza iletişim (eWOM) ve Alanya'daki restoran yorumlarının değerlendirilmesi üzerine bir araştırma. Journal of Tourism and Gastronomy Studies, 6(4), 953–973. https://doi.org/10.21325/jotags.2018.343
25. Lane, C. (2014). The cultivation of taste: Chefs and the organization of fine dining. Oxford University Press.
26. Lau, K. C., Lee, S. ve Phau, I. (2025). Michelin matters? Examining perceived value, skepticism, and dining intentions. Journal of International Consumer Marketing. 38(1), 1–15. https://doi.org/10.1080/08961530.2025.2491077
27. Litvin, S. W., Goldsmith, R. E. ve Pan, B. (2008). Electronic word-of-mouth in hospitality and tourism management. Tourism Management, 29(3), 458–468. https://doi.org/10.1016/j.tourman.2007.05.011
28. Liu, B. (2012). Sentiment analysis and opinion mining. Morgan ve Claypool. https://doi.org/10.2200/S00416ED1V01Y201204HLT016
29. Luca, M. (2016). Reviews, reputation, and revenue: The case of Yelp.com (Working Paper No. 12-016). Harvard Business School. https://www.hbs.edu/faculty/Pages/item.aspx?num=41233
30. Luca, M. ve Zervas, G. (2016). Fake it till you make it: Reputation, competition, and Yelp review fraud. Management Science, 62(12), 3412–3427. https://doi.org/10.1287/mnsc.2015.2304
31. Luo, L., Liu, L. ve Zheng, Y. (2026). When AI summary is inconsistent with aggregated rating: The role of trust, valence, and algorithmic explanation in consumer attitudes. Telematics and Informatics, 104, 102361. https://doi.org/10.1016/j.tele.2025.102361
32. Mayzlin, D., Dover, Y. ve Chevalier, J. (2014). Promotional reviews: An empirical investigation of online review manipulation. American Economic Review, 104(8), 2421–2455. https://doi.org/10.1257/aer.104.8.2421
33. Mudambi, S. M. ve Schuff, D. (2010). What makes a helpful online review? A study of customer reviews on Amazon.com. MIS Quarterly, 34(1), 185–200. https://doi.org/10.2307/20721420
34. Murphy, R. (2026). Local consumer review survey 2026: Star ratings keep rising, old reviews don't cut it. BrightLocal. https://www.brightlocal.com/research/local-consumer-review-survey/
35. Oliver, R. L. (1980). A cognitive model of the antecedents and consequences of satisfaction decisions. Journal of Marketing Research, 17(4), 460–469. https://doi.org/10.2307/3150499
36. Özen, İ. A., Uçuk, C. ve Aydemir, D. A. (2025). Evaluation of Google reviews of restaurants in Türkiye listed on the Michelin Guide Bib Gourmand list: Text mining approach. Journal of Tourism and Gastronomy Studies, 13(3), 2351–2365. https://doi.org/10.21325/jotags.2025.1667
37. Paget, S. (2023). Local consumer review survey 2023: Customer reviews and behavior. BrightLocal. https://web.archive.org/web/2023/https://www.brightlocal.com/research/local-consumer-review-survey/
38. 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
39. Perez, S. (2025, 5 Mart). Apple adds AI-powered app review summaries with iOS 18.4. TechCrunch. https://techcrunch.com/2025/03/05/apple-adds-ai-powered-app-review-summaries-with-ios-18-4/
40. Polat, H. ve Ağca, Y. (2022). Pazarlama stratejisinde önemli bir parametre olarak tüketici yorumları: Tüketici yorumlarındaki puanlamalar ile duygusal eğilimler arasındaki ilişki. Hitit Sosyal Bilimler Dergisi, 15(2), 470–488. https://doi.org/10.17218/hititsbd.1127965
41. Rita, P., Vong, C., Pinheiro, F. ve Mimoso, J. (2023). A sentiment analysis of Michelin-starred restaurants. European Journal of Management and Business Economics, 32(3), 276–295. https://doi.org/10.1108/EJMBE-11-2021-0295
42. Sands, D. B. (2025). Double-edged stars: Michelin stars, reactivity, and restaurant exits in New York City. Strategic Management Journal, 46(1), 148–176. https://doi.org/10.1002/smj.3651
43. Saydam, M. B. ve Altun, Ö. (2023). An analysis of British Michelin-starred restaurants: Guests' online reviews. British Food Journal, 125(11), 4214–4228. https://doi.org/10.1108/BFJ-03-2023-0236
44. Saydam, M. B., Arici, H. E. ve Olorunsola, V. O. (2022). Key attributes of Michelin 3-star restaurants' experiences: Evidence from TripAdvisor. Journal of Tourism and Gastronomy Studies, 10(1), 62–74. https://doi.org/10.21325/jotags.2022.978
45. Schlosser, A. E. (2005). Posting versus lurking: Communicating in a multiple audience context. Journal of Consumer Research, 32(2), 260–265. https://doi.org/10.1086/432235
46. Sezgin, M. ve Duman, A. (2023). Elektronik ağızdan ağıza pazarlama kapsamında konaklama işletmelerine yönelik çevrim içi yorumların duygu analizi yöntemiyle incelenmesi: Alanya örneği. Türk Turizm Araştırmaları Dergisi, 7(2), 244–265. https://doi.org/10.26677/TR1010.2023.1240
47. 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
48. Sridhar, S. ve Srinivasan, R. (2012). Social influence effects in online product ratings. Journal of Marketing, 76(5), 70–88. https://doi.org/10.1509/jm.10.0377
49. Temiz, S., Budak, İ., Kurtoğlu, R. ve Atsiz, O. (2025). Understanding the luxury gastronomy experience through Michelin restaurants: A netnography approach with LDA and sentiment analysis. Journal of Foodservice Business Research. 1–37. https://doi.org/10.1080/15378020.2025.2585873
50. Vásquez, C. ve Chik, A. (2015). “I am not a foodie…”: Culinary capital in online reviews of Michelin restaurants. Food and Foodways, 23(4), 231–250. https://doi.org/10.1080/07409710.2015.1102483
51. Vermeulen, I. E. ve Seegers, D. (2009). Tried and tested: The impact of online hotel reviews on consumer consideration. Tourism Management, 30(1), 123–127. https://doi.org/10.1016/j.tourman.2008.04.008
52. Xiang, Z., Du, Q., Ma, Y. ve Fan, W. (2017). A comparative analysis of major online review platforms: Implications for social media analytics in hospitality and tourism. Tourism Management, 58, 51–65. https://doi.org/10.1016/j.tourman.2016.10.001
53. Xiang, Z., Schwartz, Z., Gerdes, J. H. ve Uysal, M. (2015). What can big data and text analytics tell us about hotel guest experience and satisfaction? International Journal of Hospitality Management, 44, 120–130. https://doi.org/10.1016/j.ijhm.2014.10.013
54. Yazıcı Ayyıldız, A., ve Kuday, M. (2023). İstanbul’da bulunan Michelin yıldızlı restoranların Tripadvisor yorumlarının değerlendirilmesi. Journal of Hospitality and Tourism Issues, 5(1), 54–67. https://doi.org/10.51525/johti.1271942
55. Yetgin, D., Keküç, M. ve Şayin, M. (2020). Restoranlara yönelik Tripadvisor yorumlarının içerik analizi yöntemi ile değerlendirilmesi: İstanbul örneği. Journal of Tourism and Gastronomy Studies, 8(3), 2090–2109. https://doi.org/10.21325/jotags.2020.650