Exploring Guilin's Destination Image Via User-Generated Content: A Computational Methods

This study quantify mainland China's destination image through international tourists' user-generated content (UGC), with a specific focus on Guilin, utilizing advanced computational techniques such as Latent Dirichlet Allocation (LDA) for topic modeling and sentiment analysis. It systematically evaluates online travel reviews to distill key themes and emotional sentiments that shape Guilin's image, uncovering a rich tapestry of cognitive perceptions and affective reactions related to its natural scenery, cultural engagements, service standards, and logistical facets. The application of topic modeling and sentiment analysis provides a nuanced understanding of the cognitive and affective dimensions defining Guilin's destination image. While positive sentiments largely highlight the region's aesthetic and experiential allure, negative sentiments reveal critical areas for improvement, such as perceived value and infrastructure, which are vital for enhancing tourist satisfaction and reinforcing Guilin's appeal in the global tourism market. This research applies LDA and sentiment analysis to interpret UGC offer a calculable methodological approach for broader application in destination image studies. By aligning perceptual and emotional insights with destination marketing strategies, the findings offer actionable intelligence to optimize tourist experiences and enhance destination loyalty. This approach not only enriches the academic understanding of destination images but also provides practical frameworks for destination managers to harness the full potential of UGC in shaping and refining the global image of tourism locales.