A Deep Learning Model for Online Review Analysis to Enhance Service Quality of 1-3-Star Hotels in the Sam Buri Area
Article Sidebar
Main Article Content
Abstract
This research aims to develop a deep learning model and data-driven strategies for marketing and service enhancement by analyzing online reviews in the hotel industry across the Sam Buri area, comprising Lopburi, Saraburi, and Singburi provinces. It focuses on 1–3-star hotels, utilizing review data from Agoda. A Long Short-Term Memory (LSTM) model was employed to classify sentiments as positive, negative, or neutral based on 2,767 reviews collected between 2023 and 2024. The model achieved an overall accuracy of 0.8297. Notably, it performed well in identifying negative reviews, with precision of 0.9079, recall of 0.8920, and F1-score of 0.8999, reflecting its ability to recognize the distinct linguistic features of negative sentiment, which often uses clear and direct language. Frequent keywords in negative reviews included “room”, “breakfast”, “cleanliness”, “parking”, “bed” and “old room.” For neutral sentiment, the model showed satisfactory performance with an F1-score of 0.8510. Positive review classification yielded a lower F1-score of 0.6527, likely due to the diverse and ambiguous nature of positive expressions. Common keywords in positive reviews were “room”, “breakfast”, “cleanliness” and “good service.” Overall, the LSTM model demonstrates strong potential for practical application in sentiment analysis and text classification within the hospitality industry.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
All published articles are SJMS’s copyright. The editorial board allows all published articles to be copied, excerpted, or disseminated with academic citation.
References
Badouch, M., & Boutaounte, M. (2024). Design and implementation of a hotel recommendation system using deep learning. In AI and data engineering solutions for effective marketing (pp. 21). IGI Global.
Chinedu, J. K. (2024). Impact of online reviews hotel booking intentions among millennials in Nigeria. Journal of Hospitality and Tourism, 4(2), 1–11.
Chollet, F., & Watson, M. (2024). Deep learning with Python (3rd ed.). Manning Publications.
Daza, A., González Rueda, N. D., Aguilar Sánchez, M. S., Robles Espíritu, W. F., & Chauca Quiñones, M. E. (2024). Sentiment analysis on e-commerce product reviews using machine learning and deep learning algorithms: A bibliometric analysis, systematic literature review, challenges and future works. International Journal of Information Management Data Insights, 4(2), 100267.
El-Said, O. A. (2020). Impact of online reviews on hotel booking intention: The moderating role of brand image, star category, and price. Tourism Management Perspectives, 33, 100604.
Gabbard, D. (2023). The impact of online reviews on hotel performance. Journal of Modern Hospitality, 2(1), 26–36.
Jitboonyapinit, C., Maneerat, P., & Chirawichitchai, N. (2022). Development of a sentiment analysis model on Thai social media using deep learning techniques. Huachiew Chalermprakiet Journal of Science and Technology, 8(2), 8–18.
Klaokliang, J. (2021). Evaluating model performance Confusion Matrix Medium. Retrieved June 13, 2024, from https://nattrio.medium.com/confusionmatrix
Liu, H., Huang, M., & Zhang, P. (2025). The influence of social media marketing on the quality of hotel services and the behavioral intentions of tourists. Acta Psychologica, 255, 104881.
Nicolau, J. L., Xiang, Z., & Wang, D. (2024). Daily online review sentiment and hotel performance. International Journal of Contemporary Hospitality Management, 36(3), 790-811.
Pohuda, N. (2023). The influence of OTA channels on the tourism industry. Scientific Notes of Taurida National V I Vernadsky University Series Economy and Management, 73(2), 43-51.
Roy, G. (2023). Travelers’ online review on hotel performance Analyzing facts with the Theory of Lodging and sentiment analysis. International Journal of Hospitality Management, 111, 103459.
SiteMinder. (2024). Hotel Booking Trends. Retrieved January 10, 2025, from https://siteminder.com/th/r/hotel-classifications/
Theworldbizs. (2024). Promote the Thai Charm Festival in 5 regions, boost tourism. Retrieved March 1, 2025, form https://theworldbizs.com/2024/08/06/19643/
Tulyakawat, T. (2024). 3 challenging issues for the hotel business. Retrieved July 06, 2024, from https://krungthai.com/
Villegas, F. (2024). Word cloud generator. QuestionPro. Retrieved January 20, 2025, from https://questionpro.com/blog/
Wu, P., Sun, S., Zhou, L., Yao, Y., & Deveci, M. (2025). Platforms empower: Mining online reviews for supporting consumers decisions. Journal of Retailing and Consumer Services, 84, 104214.
Xu, W., Yao, Z., Ma, Y., & Li, Z. (2025). Understanding customer complaints from negative online hotel reviews: A BERT-based deep learning approach. International Journal of Hospitality Management, 126, 104057.
Yang, D., & Liu, P. (2025). Utilizing AI to manage rapport: ERNIE Bot’s interpersonal strategies to respond to negative hotel reviews. Lingua, 315, 103874.
Zhang, C., Cheng, X., Li, K., & Li, B. (2025). Hotel recommendation mechanism based on online reviews considering multiattribute cooperative interactive characteristics. Omega, 130, 103173.
Zhang, D., & Niu, B. (2024). Leveraging online reviews for hotel demand forecasting: A deep learning approach. Information Processing & Management, 61(1), 103527.
Zhu, J. J., Chang, Y. -C., Ku, C. -H., Li, S. Y., & Chen, C. -J. (2021). Online critical review classification in response strategy and service provider rating: Algorithms from heuristic processing, sentiment analysis to deep learning. Journal of Business Research, 129, 860–877.
