Analyzing Tourists’ Scene Preferences through Digital Footprints in World Heritage Site: A Case Study of the Grand Canal’s Tongzhou Section

Abstract World Cultural Heritage sites represent the historical value and spatial significance of human civilization, balancing cultural preservation with ecological protection. They serve not only as vessels of cultural continuity but also as key resources for tourism development. To enhance the understanding of tourist scene preferences and provide targeted strategies for future planning, this study focuses on the Tongzhou section of the Grand Canal—designated as a UNESCO World Cultural Heritage site—as a case study. By collecting content from mainstream short video platforms (primarily Douyin) and developing custom analysis tools using Python and Baidu AI Cloud APIs, the study extracts and interprets keyframes and associated textual data from videos to identify the types of scenes that capture visitors' attention, as well as variations across different heritage nodes. Results show that natural experiential scenes receive the highest level of visitor interest, while historical and cultural scenes—despite the area's rich heritage—remain underappreciated. Moreover, tourist scene preferences vary significantly between nodes, influenced by the specific characteristics of each site. Based on these findings, the study offers practical recommendations for site managers to better align interpretive and experiential offerings with visitor interests, while also addressing the needs of local residents.