Sentiment analysis and topic modelling on user-generated content in hospitality: a case study on customer perceptions in Ho Chi Minh City, Vietnam
by Thai-Doan Dang; Manh-Tuan Nguyen; Giang-Do Nguyen
J. for International Business and Entrepreneurship Development (JIBED), Vol. 16, No. 2, 2024

Abstract: This study leverages sentiment analysis and topic modelling to enhance understanding of customer perceptions in the hospitality industry, through an empirical analysis of user-generated content from Booking.com related to establishments in Ho Chi Minh City, Vietnam. By employing latent Dirichlet allocation, the research uncovers critical themes impacting customer satisfaction, including service quality, the overall hotel experience, location convenience, dining options, and room comfort and cleanliness. The effectiveness of various machine learning (ML) and deep learning (DL) models is evaluated for sentiment analysis. The convolutional neural network model, in particular, demonstrates superior performance with an accuracy of 0.95 and an F1-score of 0.97. Highlighting the application of sophisticated ML and DL techniques to analyse complex patterns in user-generated feedback, this research study offers valuable insights into brand equity and customer experiences within the hospitality sector.

Online publication date: Fri, 06-Sep-2024

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the J. for International Business and Entrepreneurship Development (JIBED):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com