Skripsi
ANALISIS SENTIMEN BERBASIS ASPEK TERHADAP TAMAN WISATA ALAM PUNTI KAYU BERDASARKAN ULASAN PENGGUNA GOOGLE MAPS
Tourism as one of the sectors that contribute to economic growth in Indonesia requires special attention to be continuously evaluated. Traveler reviews on social media such as Google Maps can be used to evaluate the quality of tourist attractions. This research focuses on conducting an aspect-based sentiment analysis of one of the tourist attractions in Palembang, namely Punti Kayu Nature Park on Google Maps user reviews. The aspects used are the six aspects of tourism recommended by the World Tourism Organization (WTO), namely Attractions, Amenities, Accessibility, Image, Price, and Human Resources. Sentiment classification was performed using machine learning models, namely Logistic Regression (LR) and Support Vector Machine (SVM), and transfer learning models, namely BERT and IndoBERT in four different experimental scenarios. The best experimental results with an F1 score of 98.22% were achieved by the IndoBERT model with the third scenario using data pre-processing techniques, namely case folding, emoji processing, removing unnecessary characters, text normalization, and stemming, without stopwords removal.