Scholarlink

<p>Understanding tourist behavioral patterns and perceptual preferences is crucial for effective destination management and sustainable tourism development. This study proposes an analytical framework integrating spatial, temporal, and semantic information to analyze tourist behavior patterns and perceptual preferences using user-generated content (UGC) data from Sina Weibo, with Beijing as a case study. The results reveal that 54 tourist hotspots were identified using the ST-DBSCAN clustering method, uncovering spatial distribution characteristics where tourism attractions are concentrated in the central city area and dispersed in suburban areas. Five types of tourist travel path patterns were recognized, with seasonal fluctuations influenced by the interaction of holiday duration and climatic conditions. Tourist visitation volumes also exhibited significant seasonal variations, peaking in summer and autumn while declining in winter due to cold weather conditions. Semantic analysis results indicate that changes in high-frequency words reveal differences in the temporal variation of attraction appeal across different types of tourist attractions. BERTopic modeling extracted five major themes and 37 subtopics, reflecting the diversity of tourist preferences. This study provides scientific guidance for tourism destination management in Beijing and validates the proposed framework’s applicability in problem identification and decision support.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Analysis of Tourist Behavior Patterns and Perceptions in Beijing Based on User-Generated Content Data

  • 期刊论文

  • 发表日期：

    2025年8月13日

查看全文
  • Xiaohang Li,
  • Tong Yang,
  • Bin Meng,
  • Siyu Chen,
  • Shuying Zhang

摘要

Understanding tourist behavioral patterns and perceptual preferences is crucial for effective destination management and sustainable tourism development. This study proposes an analytical framework integrating spatial, temporal, and semantic information to analyze tourist behavior patterns and perceptual preferences using user-generated content (UGC) data from Sina Weibo, with Beijing as a case study. The results reveal that 54 tourist hotspots were identified using the ST-DBSCAN clustering method, uncovering spatial distribution characteristics where tourism attractions are concentrated in the central city area and dispersed in suburban areas. Five types of tourist travel path patterns were recognized, with seasonal fluctuations influenced by the interaction of holiday duration and climatic conditions. Tourist visitation volumes also exhibited significant seasonal variations, peaking in summer and autumn while declining in winter due to cold weather conditions. Semantic analysis results indicate that changes in high-frequency words reveal differences in the temporal variation of attraction appeal across different types of tourist attractions. BERTopic modeling extracted five major themes and 37 subtopics, reflecting the diversity of tourist preferences. This study provides scientific guidance for tourism destination management in Beijing and validates the proposed framework’s applicability in problem identification and decision support.