What do the customers of fine-dining restaurants write about? The themes-modelling of textual guest reviews of such restaurants with a neural topic modelling method
DOI:
https://doi.org/10.14267/TURBULL.2025v25n1.2Keywords:
neural topic modelling, restaurant reviews, fine dining, BERTopicAbstract
This paper analyses the themes of textual guest reviews of fine dining restaurants in Budapest using BERTopic, a neural topic modelling method. The study analyses 10,962 English-language reviews from Tripadvisor collected between 2007 and March 2024. Traditional topic modelling methods have limitations, especially for short texts. BERTopic offers semantically more coherent topic identification by utilising Sentence-BERT embeddings. In the topic modelling of guest reviews, 40 topics were identified covering almost all aspects of restaurant service. We examined the relationship between the number of guest reviews and the themes identified themes, and how the proportion of certain themes in the reviews changed over time. The research concluded that, although, BERTopic has limitations, it shows promise in analysing large amounts of textual data.
References
ABUZAYED, A. – AL-KHALIFA, H. (2021): BERT for Arabic Topic Modeling: An Experimental Study on BERTopic Technique. Procedia Computer Science. 189. pp. 191–194. https://doi. org/10.1016/j.procs.2021.05.096
AKTAS-POLAT, S. (2022): Analysis of Fine Dining Restaurant Reviews for Perception of Customers Restaurant Service Quality. Journal of Tourism and Gastronomy Studies. https://doi. org/10.21325/jotags.2022.974
ALAMSYAH, A. – GIRAWAN, N. D. (2023): Improving Clothing Product Quality and Reducing Waste Based on Consumer Review Using RoBERTa and BERTopic Language Model. Big Data and Cognitive Computing. 7(4). 168. https://doi.org/10.3390/bdcc7040168
ALBALAWI, R. – YEAP, T. H. – BENYOUCEF, M. (2020): Using Topic Modeling Methods for Short-Text Data: A Comparative Analysis. Frontiers in Artificial Intelligence. 3. https://doi. org/10.3389/frai.2020.00042
BLEI, D. M. (2012): Probabilistic topic models. Communications of the ACM. 55(4). pp. 77–84. https://doi.org/10.1145/2133806.2133826
BLEI, D. M. – NG, A. Y. – JORDAN, M. I. (2003): Latent Dirichlet allocation. Journal of Machine Learning Research. 3(4-5). https://doi. org/10.1016/b978-0-12-411519-4.00006-9
CHANG, J. – GERRISH, S. – WANG, C. – BOYD GRABER, J. – BLEI, D. (2009): Reading Tea Leaves: How Humans Interpret Topic Models. Advances in Neural Information Processing Systems. 22. https:// proceedings.neurips.cc/paper_files/paper/2009/ hash/f92586a25bb3145facd64ab20fd554ff Abstract.html
CHEN, Z. – DOSS, H. (2019): Inference for the Number of Topics in the Latent Dirichlet Allocation Model via Bayesian Mixture Modeling. Journal of Computational and Graphical Statistics. 28. pp. 567–585. https://doi.org/10.108 0/10618600.2018.1558063
CHENG, X. – YAN, X. – LAN, Y., – GUO, J. (2014): BTM: Topic Modeling over Short Texts. IEEE Transactions on Knowledge and Data Engineering. 26(12). pp. 2928–2941. IEEE Transactions on Knowledge and Data Engineering. https://doi. org/10.1109/TKDE.2014.2313872
DE GROOT, M. – ALIANNEJADI, M. – HAAS, M. R. (2022): Experiments on Generalizability of BERTopic on Multi-Domain Short Text. ArXiv. https://arxiv.org/abs/2212.08459
DEVLIN, J. – CHANG, M.-W. – LEE, K. – TOUTANOVA, K. (2019): BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. ArXiv abs/1810.04805. https:// doi.org/10.48550/arXiv.1810.04805
EGGER, R. – YU, J. (2022): A Topic Modeling Comparison Between LDA, NMF, Top2Vec, and BERTopic to Demystify Twitter Posts. Frontiers in Sociology. 7. 886498. https://doi.org/10.3389/ fsoc.2022.886498
GEORGE, C. P. – DOSS, H. (2018): Principled Selection of Hyperparameters in the Latent Dirichlet Allocation Model. Journal of Machine Learning Research. 18(162). pp. 1–38. http://jmlr. org/papers/v18/15-595.html
GLAZKOVA, A. (2021): Identifying Topics of Scientific Articles with BERT-Based Approaches and Topic Modeling. In: Gupta, M. – Ramakrishnan, G. (szerk.): Trends and Applications in Knowledge Discovery and Data Mining. Springer International Publishing. pp. 98–105. https://doi.org/10.1007/978-3-030- 75015-2_10
GRIFFITHS, T. L. – STEYVERS, M. (2004): Finding scientific topics. Proceedings of the National Academy of Sciences. 101(suppl_1). pp. 5228– 5235. https://doi.org/10.1073/pnas.0307752101
GROOTENDORST, M. (2022): BERTopic: Neural topic modeling with a class-based TF-IDF procedure. ArXiv abs/2203.05794. https://doi. org/10.48550/arXiv.2203.05794
HA, C. – TRAN, V.-D. – NGO VAN, L. – THAN, K. (2019): Eliminating overfitting of probabilistic topic models on short and noisy text: The role of dropout. International Journal of Approximate Reasoning. 112. pp. 85–104. https://doi. org/10.1016/j.ijar.2019.05.010
HUANG, J. – ROGERS, S. – JOO, E. (2014): Improving Restaurants by Extracting Subtopics from Yelp Reviews. iConference 2014 (Social Media Expo). https://hdl.handle.net/2142/48832
KOROTEEV, M. V. (2021): BERT: A Review of Applications in Natural Language Processing and Understanding. ArXiv. https://arxiv.org/ abs/2103.11943
KRISHNAN, A. (2023): Exploring the Power of Topic Modeling Techniques in Analyzing Customer Reviews: A Comparative Analysis. ArXiv. abs/2308.11520. https://doi.org/10.48550/ ARXIV.2308.11520
KWON, W. – LEE, M. – BACK, K.-J. (2020): Exploring the underlying factors of customer value in restaurants: A machine learning approach. International Journal of Hospitality Management. 91. 102643. https://doi. org/10.1016/j.ijhm.2020.102643
KWON, W. – LEE, M. – BOWEN J. T. (2022): Exploring Customers’ Luxury Consumption in Restaurants: A Combined Method of Topic Modeling and Three-Factor Theory. Cornell Hospitality Quarterly. 63(1). pp. 66‒7. https://doi. org/10.1177/19389655211037667
OGUNLEYE, B. – MASWERA, T. – HIRSCH, L. – GAUDOIN, J. – BRUNSDON, T. (2023): Comparison of Topic Modelling Approaches in the Banking Context. Applied Sciences. 13(2). 797. https://doi.org/10.3390/app13020797
PARK, E. – CHAE, B., – KWON, J. (2018): The structural topic model for online review analysis: Comparison between green and non green restaurants. Journal of Hospitality and Tourism Technology. 11(1). pp. 1–17. https://doi. org/10.1108/JHTT-08-2017-0075
RIEGER, J. – RAHNENFÜHRER, J. – JENTSCH C. (2020): Improving Latent Dirichlet Allocation: On Reliability of the Novel Method LDAPrototype. Natural Language Processing and Information Systems. 12089. pp. 118–125. https:// doi.org/10.1007/978-3-030-51310-8_11
LOVATO, P. – BICEGO, M. – MURINO, V. – PERINA, A. (2015): Robust Initialization for Learning Latent Dirichlet Allocation. In: Feragen, A. – Pelillo, M. – Loog, M. (eds): Similarity-Based Pattern Recognition. SIMBAD 2015. Lecture Notes in Computer Science. 9370. Springer, Cham. pp. 117–132. https://doi. org/10.1007/978-3-319-24261-3_10
QIANG, J. – QIAN, Z. – LI, Y. – YUAN, Y. – WU, X. (2022): Short Text Topic Modeling Techniques, Applications, and Performance: A Survey. IEEE Transactions on Knowledge and Data Engineering. 34(3). pp. 1427–1445. https://doi.org/10.1109/ TKDE.2020.2992485
TITOV, I. – McDONALD, R. (2008): Modeling Online Reviews with Multi-grain Topic Models. ArXiv. https://arxiv.org/abs/0801.1063
WESTERLUND, M. – SHAIRY, Z. – LEMINEN, S. – RAJAHONKA, M. (2019): Topic modelling analysis of online reviews: Indian restaurants at Amazon.com. In: Bitran, I. – Conn, S. – Gernreich, C. – Heber, M. – Huizingh, E. – Kokshagina, O. – Torkkeli, M. – Tynnhammar , M. (eds): Proceedings of the ISPIM Connecs Ottawa Conference. ISPIM. pp. 1-14.
ZHANG, S. – LY, L. – MACH, N. – AMAYA, C. (2022): Topic Modeling and Sentiment Analysis of Yelp Restaurant Reviews. International Journal of Information Systems in the Service Sector (IJISSS). 14(1). pp. 1–16. https://doi.org/10.4018/ IJISSS.295872
ZHAO, F. – LIU, H. (2023): Modeling customer satisfaction and revisit intention from online restaurant reviews: An attribute-level analysis. Industrial Management – Data Systems. 123(5). pp. 1548–1568. https://doi.org/10.1108/IMDS 09-2022-0570
ZUO, Y. – LI, C. – LIN, H. – WU, J. (2023): Topic Modeling of Short Texts: A Pseudo-Document View With Word Embedding Enhancement. IEEE Transactions on Knowledge and Data Engineering. 35(1). pp. 972–985. IEEE Transactions on Knowledge and Data Engineering. https:// doi.org/10.1109/TKDE.2021.3073195
