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

User-generated content (UGC) offers large-scale, naturalistic data for examining tourism destination image. Focusing on the Historic Centre of Macao (HCM), a World Cultural Heritage site, this study collected 3781 tourist reviews from Rednote, Ctrip, Dianping, and TripAdvisor and developed a multi-model text-mining framework integrating TF-IDF, BERTopic, and RoBERTa. The results show that HCM’s online tourism image comprises four dimensions: perceptions of history, culture, and heritage value; perceptions of spatial landmarks and urban landscapes; modes of travel behavior and embodied experience; and emotional evaluation and tourism experience quality. The TF-IDF results indicate that terms such as architecture, history, Portuguese, church, Ruins of St. Paul’s, and Senado Square constitute the core elements of tourists’ cognitive image. BERTopic further identified 18 valid topics and revealed three interrelated semantic clusters: heritage-space cognition, landmark and district experiences, and integrated tourism experiences. The RoBERTa-based sentiment analysis shows that tourists’ overall evaluations are dominated by positive emotions, while crowding, high visitor density, and gaps between expectations and actual experiences remain important sources of negative evaluations. This study demonstrates the applicability of the proposed framework in the Historic Centre of Macao and provides a methodological reference for tourism image research in other cultural heritage destinations.