<![CDATA[This study aims to identify spatial patterns of artificial tourist attractions and extract key visitor concerns to support urban tourism planning. To achieve this objective, spatial clustering and sentiment analysis were applied sequentially as complementary analytical approaches. The DBSCAN algorithm was used to group 62 artificial tourist attractions into five spatially coherent clusters based on geographic proximity. In parallel, Natural Language Processing (NLP) techniques were employed to analyze 2,800 online visitor reviews and classify dominant sentiment themes. The results reveal distinct spatial structures of attractions and recurring negative issues related to pricing transparency, parking availability, food quality, accessibility, and facility conditions. Using Batu City, Indonesia, as a case study, this research demonstrates how integrating geospatial analysis with user-generated content can transform informal digital feedback into policy-relevant insights. The proposed framework offers a practical, data-driven approach for informing tourism governance and planning decisions in emerging urban tourism destinations.]]>
Copyrights © 2025
