Analisa Sentimen Indonesia Mengenai KRL Commuter Line Menggunakan Metode Naïve Bayes dan Support Vector Machine
Adrian Nathanael Kalalo, Een Juhriah, Akhmad Aris Tantowi · STRING (Satuan Tulisan Riset dan Inovasi Teknologi) · 2025
This study analyzes the sentiment of Indonesian society towards KRL Commuter Line services using Naive Bayes and Support Vector Machine (SVM) methods. Data was collected from Twitter through an API and processed through a series of preprocessing steps, including the removal of special characters, URLs, and other irrelevant information. Lexicon-based labeling was performed to identify the sentiment as positive, negative, or neutral for each tweet. The Naive Bayes and SVM models were then trained and tested on the labeled data. The results indicate that both methods are effective in classifying sentiment; however, SVM outperforms Naive Bayes in terms of accuracy. These findings highlight the significant potential of both methods in sentiment analysis, with SVM being the more suitable choice for this particular case. This study is expected to contribute to the improvement of KRL Commuter Line services by providing insights into user sentiment, which can be used as a basis for service enhancement.