<![CDATA[The implementation of the Free Nutritious Meal Program (Makan Bergizi Gratis/MBG) as a strategic government initiative has generated diverse responses from the public, widely discussed on social media, particularly on the X (Twitter) platform. Differences in perceptions regarding the objectives, implementation, and impacts of the policy have encouraged intensive public discussions. However, the tendency of public sentiment toward this program has not been widely analyzed systematically using machine learning approaches based on contextual representations. Therefore, this study analyzes public sentiment toward the hashtag #MakanBergiziGratis using the Long Short-Term Memory (LSTM) method. A total of 5,516 Indonesian-language tweets were collected through a web scraping process within the period of January 1 to November 30, 2025. Sentiment labeling employed a lexicon-based approach to classify the data into three categories: positive, neutral, and negative. The analysis stages included text preprocessing, BERT tokenization and embedding, handling imbalanced data using the Synthetic Minority Over-sampling Technique (SMOTE), and sentiment classification using LSTM. The results reveal that neutral sentiment dominates with 60.80%, followed by positive sentiment at 34.34% and negative sentiment at 4.86%. The developed model achieved an accuracy of 82.50% with a weighted F1-score of 82.66%. Furthermore, evaluation using 5-fold cross-validation produced an average accuracy of 82.8%, indicating stable model performance and good generalization capability in identifying public opinion trends toward the MBG policy.]]>
