Analisis Sentimen Ulasan Turis Terhadap Objek Wisata di Bali Menggunakan Algoritma Support Vector Machine

Tourism in Bali plays a significant role in the regional economy, and tourist reviews can provide valuable insights into the quality of experiences encountered. This study aims to analyze the sentiment of English-language tourist reviews for four major tourist attractions in Bali, namely Kuta Beach, Nusa Dua Beach, Sanur Beach, and Tegalalang Rice Terrace, with 720 reviews each. The data was obtained from the TripAdvisor website and analyzed through several stages, including web scraping, text preprocessing, transformation using Term Frequency–Inverse Document Frequency (TF-IDF), and modeling using the Support Vector Machine (SVM) algorithm. Evaluation results show that the Support Vector Machine (SVM) algorithm is capable of classifying sentiment with the highest accuracy of 91.49% when using balanced data, and 88.125% with imbalanced data. These findings indicate that the model performs better when the sentiment distribution in the dataset is balanced. Overall, the Support Vector Machine (SVM) algorithm proves to be effective and accurate in analyzing tourist sentiment toward tourist attractions in Bali.