Spatiotemporal Behavior and Hotspot Analysis of Tourists in Yuntai Mountain Scenic Area Based on Multi-source Data

Zhipeng Yang

doi:10.63313/SD.9006

Authors

Zhipeng Yang College of Surveying and Land Information Engineering, Henan Polytechnic University, Jiaozuo 454000, China. Author

DOI:

https://doi.org/10.63313/SD.9006

Keywords:

Tourist spatiotemporal behavior, Multi-source data, Online attention, DC-DBSCAN clustering, Virtual-real coupling, Yuntai Mountain Scenic Area

Abstract

Selecting Yuntai Mountain Scenic Area as the case study, this research integrates multi-source heterogeneous data, including social media texts and tourist GNSS trajectories. By comprehensively applying the Analytic Hierarchy Process (AHP) and Direction-Constrained DBSCAN (DC-DBSCAN), it analyzes the characteristics of tourists' online attention and physical spatiotemporal behaviors, constructing a virtual-real coupling response mechanism for the scenic area. The results show: (1) The online attention of Yuntai Mountain Scenic Area exhibits an alternating "stable-pulse" fluctuation pattern, significantly influenced by statutory holidays, with tourists' focus concentrated on core attractions and considerable negative emotional feedback regarding physical exertion. (2) The physical flow of tourists demonstrates a temporal rhythm of "early entry, late exit, and single-peak aggregation." Spatially, a core skeleton road network primarily consisting of Fenghuang Ridge and Hongshi Gorge is formed. The duration of stay presents a bimodal clustering characteristic of short-term check-ins and in-depth experiences. (3) There is a significant spatiotemporal divergence between online attention and offline physical flow. Temporally, the rise in online heat precedes the peak of physical tourist flow by 1-2 weeks; spatially, Hongshi Gorge shows a virtual-real balance, Zhuyu Peak exhibits online overheating, while experiential attractions like Fenghuang Ridge and Xiaozhai Valley present significant offline overheating.

References

[1] Zhu, Y. (2023). Notice of the Ministry of Culture and Tourism on issuing the "Domestic Tourism Improvement Plan (2023-2025)". State Council Department Documents, Chinese Government Network. Retrieved November 10, 2024, from https://www.gov.cn/zhengce/zhengceku/202311/content_6914996.htm. (in Chinese)

[2] Yang, Y. (2008). Industrial integration: A new perspective on the development trend of tourism industry. Tourism Science, (4), 6-10. DOI:10.16323/j.cnki.lykx.2008.04.002. (in Chinese)

[3] Lv, L. (2024). Notice of the Ministry of Culture and Tourism and other departments on issuing the "Guiding Opinions on Promoting the High-Quality Development of Tourism Public Services". State Council Department Documents, Chinese Government Network. Retrieved November 10, 2024, from https://www.gov.cn/zhengce/zhengceku/202408/content_6966756.htm. (in Chinese)

[4] Huang, W., Liu, Y., & Zhou, D. (2025). Multi-platform evolution path and empirical study of public emergency network public opinion based on information ecology theory. Journal of Intelligence, 44(9). (in Chinese)

[5] Wang, Y., & Ma, H. (2025). Network public opinion prediction based on multi-dimensional feature modeling of high-impact figures. Computer Applications and Software. (in Chinese)

[6] Zheng, X., Wang, F., Li, J., et al. (2024). Pattern and cause of tourism flow in Tibet based on tourist GPS trajectory big data. Economic Geography, 44(11). https://doi.org/10.15957/j.cnki.jjdl.2024.11.022. (in Chinese)

[7] Zhang, H., Chang, Q., Xie, Y., et al. (2025). Spatiotemporal characteristics of recreation behavior in Wuyishan National Park based on multi-source data. Tourism Science, 39(3). https://doi.org/10.16323/j.cnki.lykx.2025.03.004. (in Chinese)

[8] Yin, J., Xie, S., Qiao, H., et al. (2025). Spatiotemporal behavior characteristics and pattern clustering of tourists in eco-tourism destinations of Shennongjia Forestry District. Scientia Geographica Sinica, 45(5). https://doi.org/10.13249/j.cnki.sgs.20240475. (in Chinese)