Authors : Petcharat Phuttakij; Bandhita Plubin; Walaithip Bunyatisai; Thanasak Mouktonglang; Suwika Plubin

Volume/Issue : Volume 10 - 2025, Issue 2 - February

Google Scholar : https://tinyurl.com/bddtuf6u

Scribd : https://tinyurl.com/ynkx9bxk

DOI : https://doi.org/10.5281/zenodo.14979444

Abstract : The rapid growth of the tourism and hospitality industry has resulted in a significant increase in customer reviews shared online. These reviews help tourists discover new accommodations with a favorable atmosphere and reasonable prices; the volume of reviews makes it challenging for travelers to choose the right option. Negative reviews, in particular, can influence booking decisions and impact a hotel’s image. Sentiment analysis that categorizes comments has become an important tool for analyzing customer feedback automatically. Moreover, the Thai language has unique characteristics, such as its diverse writing styles, punctuation, and multiple meanings of a single word, which pose language barriers for sentiment analysis. Our method, employing the Bidirectional Encoder Representations from Transformers (BERT) model, analyzes hotel reviews in Thai, classifying sentiments into three categories: positive, neutral, and negative. This study uses a dataset of 37,011 hotel reviews. Our experiment results show that the BERT model has an accuracy of 89.31% and an F1 score of 89.43%, outperforming prior research. The findings contribute insights to a deeper understanding of customer reviews for the hospitality industry, enabling hotel operators to respond to customer feedback more effectively and improve their services. Analyzing and distilling reviews from customer feedback may assist tourists and others in making quicker choices. Finally, the results of this study show that using BERT for sentiment analysis can help businesses grow and become more competitive in the quickly changing tourism market.

Keywords : Sentiment Analysis, Thai Language, Hotel Reviews, BERT, Natural Language Processing.

References :

1. Areshey, A., &Mathkour, H. (2023). Transferlearning for sentiment classification using bidirectional encoder representations from transformers (BERT) model. Sensors, 23(11), 5232.
2. Arrar, D., Kamel, N., &Refoufi, A. (2024). Implicit Sentiment Analysis of Hotel Comments for Disaster Management: A Comparative Study of Machine Learning, Deep Learning, and BERT Model. In 2024 International Conference on Information and Communication Technologies for Disaster Management (ICT-DM) (pp. 1-7). IEEE.
3. Bimaputra, D. S., &Sutoyo, E. (2023). Aspect-Based Sentiment Analysis of Hotels in Bali on Tripadvisor Using BERT Algorithm. International Journal of Advances in Data and Information Systems, 4(1), 29-40.
4. Bowornlertsutee, P., &Paireekreng, W. (2022). The Model of Sentiment Analysis for Classifying the Online Shopping Reviews. Journal of Engineering and Digital Technology (JEDT), 10(1), 71-79.
5. Devlin, J. (2018). Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805.
6. Harnmetta, P., &Samanchuen, T. (2022). Sentiment analysis of thai stock reviews using transformer models. In 2022 19th International Joint Conference on Computer Science and Software Engineering (JCSSE) (pp. 1-6). IEEE.
7. Innork, K., Polpinij, J., Namee, K., Kaenampornpan, M., Saisangchan, U., &Wiangsamut, S. (2023). A Comparative Study of Multi-Class Sentiment Classification Models for Hotel Customer Reviews. In 2023 Research, Invention, and Innovation Congress: Innovative Electricals and Electronics (RI2C) (pp. 88-92). IEEE.
8. Koroteev, M. V. (2021). BERT: a review of applications in natural language processing and understanding. arXiv preprint arXiv:2103.11943.
9. LemaÃŽtre, G., Nogueira, F., & Aridas, C. K. (2017). Imbalanced-learn: A python toolbox to tackle the curse of imbalanced datasets in machine learning. Journal of machine learning research, 18(17), 1-5.
10. Luo, H., Ji, L., Li, T., Duan, N., & Jiang, D. (2020). GRACE: Gradient harmonized and cascaded labeling for aspect-based sentiment analysis. arXiv preprint arXiv:2009.10557.
11. Maity, K., Poornash, A. S., Bhattacharya, S., Phosit, S., Kongsamlit, S., Saha, S., &Pasupa, K. (2024). HateThaiSent: Sentiment-Aided Hate Speech Detection in Thai Language. IEEE Transactions on Computational Social Systems.
12. Matarat, K. (2024). Enhancing Hotel Management: a Sentiment Analysis Approach to Assessing Customer Impressions on Environment-Based Reviews. International Journal of Professional Business Review, 9(1), e04152-e04152.
13. Pasupa, K., & Ayutthaya, T. S. N. (2019). Thai sentiment analysis with deep learning techniques: A comparative study based on word embedding, POS-tag, and sentic features. Sustainable Cities and Society, 50, 101615.
14. Porntrakoon, P., Moemeng, C., &Santiprabhob, P. (2021). Text summarization for Thai food reviews using simplified sentiment analysis. In 2021 18th international joint conference on computer science and software engineering (JCSSE) (pp. 1-5). IEEE.
15. Pramudya, Y. G., & Alamsyah, A. (2023). Hotel Reviews Classification and Review-based Recommendation Model Construction using BERT and RoBERTa. In 2023 6th International Conference on Information and Communications Technology (ICOIACT) (pp. 437-442). IEEE.
16. Pugsee, P., &Ongsirimongkol, N. (2019, November). A classification model for Thai statement sentiments by deep learning techniques. In Proceedings of the 2019 2nd International Conference on Computational Intelligence and Intelligent Systems (pp. 22-27).
17. Sangsavate, S., Sinthupinyo, S., &Chandrachai, A. (2023). Experiments of Supervised Learning and Semi-Supervised Learning in Thai Financial News Sentiment: A Comparative Study. ACM Transactions on Asian and Low-Resource Language Information Processing, 22(7), 1-36.
18. Sungsri, T., &Ua-apisitwong, U. (2017). The analysis and summarizing system of thaihotel reviews using opinion mining technique. In Proceedings of the 5th International Conference on Information and Education Technology (pp. 167-170).
19. Vaswani, A. (2017). Attention is all you need. Advances in Neural Information Processing Systems.
20. Wu, Y., Jin, Z., Shi, C., Liang, P., & Zhan, T. (2024). Research on the Application of Deep Learning-based BERT Model in Sentiment Analysis. arXiv preprint arXiv:2403.08217.