<![CDATA[The tourism potential of waterfalls in Central Lombok Regency is quite prominent; however, it has not been fully optimized. With the advancement of digital technology, user reviews on online platforms can serve as valid indicators to assess the quality of a tourist destination. This study aims to analyze the sentiment of visitor reviews regarding waterfall tourist attractions using the Support Vector Machine (SVM) algorithm. Data were collected through web scraping from Google Maps, then processed through several preprocessing stages, automatically labeled using IndoBERT, and features were extracted using the TF-IDF method. A total of 1,250 reviews were analyzed and classified into three sentiment categories: positive, neutral, and negative. Three types of SVM algorithms were tested: LinearSVC, RBF kernel, and Polynomial kernel. Based on the results, LinearSVC achieved the best performance with an accuracy of 84% and an F1-score of 86%. These findings indicate that a machine learning-based approach, particularly SVM, is highly effective in automatically and systematically identifying visitor perceptions. The resulting data may also serve as a reference in developing tourism policies grounded in empirical evidence.]]>
Copyrights © 2025
