Tweet Sentiment Classification Towards Mobile Services Using Naive Bayes and Support Vector Machine

Abstract

This research focuses on sentiment classification of Indonesian-language tweets related to mobile service providers by integrating Support Vector Machine (SVM) and Term Frequency-Inverse Document Frequency (TF-IDF) as the main text representation method. The dataset was sourced from Twitter API and public collections, then went through preprocessing, feature extraction, model training, and performance evaluation phases. The SVM model utilizing TF-IDF exhibited perfect evaluation metrics—100% in accuracy, precision, recall, and F1-score—on the test set, indicating excellent proficiency in detecting both positive and negative sentiments. Nevertheless, such flawless results should be interpreted carefully, as they may suggest limited data diversity. This study contributes to the advancement of sentiment analysis techniques for short and informal Indonesian-language texts on social media platforms.