Aspect-Based Sentiment Analysis in Bromo Tengger Semeru National Park Indonesia Based on Google Maps User Reviews

Technology can influence and shape a person's behavior patterns when planning tours, traveling, after traveling. Visitors' reviews be used as evaluation material to improve the quality of tourist destinations become determining factor for other tourists visit or revisit destinations. The process utilizing these done by assessing aspects based on from visitors. This study aims conduct an aspect-based sentiment analysis one in Indonesia, namely Bromo Tengger Semeru National Park, Google Maps users. consist attractions, facilities, access, price. classification model is machine learning consisting SVM, Complement Naïve Bayes, Logistic Regression, transfer pre-trained BERT, IndoBERT, mBERT. Based experimental results, IndoBERT achieved best performance with accuracy F1-Score 91.48% 71.56%, respectively. In addition, among models used, SVM gives results 89.16% 62.23%.