<![CDATA[Public sentiment toward government budget efficiency policies has become increasingly visible through social media platforms, where citizens actively express opinions, support, and criticism. This study aims to analyze public sentiment toward budget efficiency policies using data collected from the social media platform X (formerly Twitter). A total of 2,000 public comments related to budget efficiency policies were collected through web scraping using the X API. The data were preprocessed through normalization, case folding, text cleaning, tokenization, stopword removal, and stemming. Sentiment classification was conducted using three machine learning algorithms: Naive Bayes, Support Vector Machine (SVM), and Random Forest. Model performance was evaluated using accuracy, precision, recall, and F1-score. The results indicate that SVM achieved the highest accuracy, while Random Forest demonstrated superior recall in identifying positive sentiment. These findings suggest that Random Forest is particularly suitable for sentiment analysis tasks where minimizing false negatives is important, while SVM performs well in overall classification accuracy. This research contributes to the comparative evaluation of machine learning models for public sentiment analysis on policy-related issues using social media data. ]]>
Copyrights © 2025
