Unveiling dynamic determinants of tourism competitiveness : analysis integrating multimodal data and spatiotemporal machine learning

Abstract

Maintaining tourism competitiveness is crucial for destinations’ long-term success. However, studies often lack longitudinal analyses that capture the evolving determinants of tourism competitiveness in both domestic and international markets. Taking China as a case study, this research introduces an innovative framework that integrates spatiotemporal machine learning with multimodal big data to examine dynamic factors influencing domestic and international tourism competitiveness. Several findings emerge: (1) overall, online popularity is essential for domestic tourism competitiveness, whereas the natural environment underpins international tourism competitiveness; (2) temporally, tourism infrastructure, government support, and online tourist perception are becoming more critical for tourism competitiveness over time, while tourism attractions’ role is waning; and (3) developed destinations are increasingly leveraging tourism infrastructure to enhance competitive advantage, and less-developed areas are benefiting more from online visibility. This research further contextualizes the dynamic nature of tourism competitiveness and offers strategies for sustainable tourism development. Also available in Chinese. See Supplemental Material for details.