<![CDATA[Online gambling is a social issue currently in the spotlight in Indonesia. Although the government, particularly the Ministry of Communication and Digital (Kemkomdigi), has taken various measures, such as blocking websites and conducting digital literacy campaigns, online gambling remains rampant and has sparked various public reactions. Social media, particularly Instagram, has become a public space where people express their opinions and sentiments regarding government performance. This study aims to classify public sentiment based on comments directed at the official Kemkomdigi Instagram account regarding the issue of online gambling. This study uses two machine learning algorithms, Random Forest and XGBoost, to compare the effectiveness of the models in classifying positive and negative sentiment. A total of 724 comments were collected and manually labeled by three annotators using a voting method. Preprocessing included cleaning, case folding, tokenization, normalization, stopword removal, and stemming. Feature representation was performed using the TF-IDF method. The data was split with a 70:30 ratio and balanced using Random Oversampling. Model training used 10-fold cross-validation and hyperparameter tuning through GridSearchCV. The evaluation results showed that the tuned Random Forest performed the best, with an accuracy of 0.7082. These findings demonstrate that machine learning approaches, particularly Random Forest, are effective in automatically identifying public sentiment toward emerging public policy issues on social media.]]>
