A Multi-Model Text Mining Approach to Tourism Image Analysis of the Historic Centre of Macao Based on User-Generated Content

A multi-model text mining analysis of user-generated content reveals that the tourism image of Macao's Historic Centre, a UNESCO World Heritage site, is shaped by four key dimensions: perceptions of history and heritage value, spatial landmarks, travel behavior, and emotional evaluation. The study, which analyzed 3781 tourist reviews using TF-IDF, BERTopic, and RoBERTa models, identified 18 topics clustered into three semantic groups—heritage-space cognition, landmark experiences, and integrated tourism experiences—and highlighted positive sentiment dominance while noting issues like crowding as sources of negative feedback. This approach offers a robust framework for assessing tourism images in cultural heritage destinations.

Xu, X., & Zhang, Q. (2026). A Multi-Model Text Mining Approach to Tourism Image Analysis of the Historic Centre of Macao Based on User-Generated Content. Buildings, 16(14), 2902. https://doi.org/10.3390/buildings16142902