Sentiment Analysis of Tourists’ Perceptions of Ubud as a World Gastronomy Destination Using the Lexicon-SVM Method

Abstract

The development of Ubud as a sustainable gastronomic tourism destination requires an understanding of tourist perceptions derived from digital platforms. This study analyzes tourist sentiment toward Ubud’s gastronomy using English-language reviews from TripAdvisor and X (formerly Twitter) through a hybrid Lexicon–Support Vector Machine (SVM) approach. A total of 28,550 reviews were analyzed, consisting of 23,647 TripAdvisor reviews and 4,903 X posts. The methodology includes data collection, text preprocessing, sentiment labeling using the VADER (Valence Aware Dictionary and Sentiment Reasoner) lexicon, TF-IDF (Term Frequency–Inverse Document Frequency), and SVM classification, with performance evaluated using standard classification metrics. The results indicate that positive sentiment dominates on both platforms, with the SVM model achieving accuracies of 89.7% on X data and 92.31% on TripAdvisor data. Word cloud analysis shows that tourist perceptions are shaped not only by food quality but also by service, atmosphere, and price, demonstrating the effectiveness of the hybrid Lexicon–SVM approach in supporting sustainable gastronomic tourism development in Ubud.