<![CDATA[The Free Nutritious Meal Program is a national policy initiated by the Indonesian government to improve the nutritional status of school-aged children and support long-term human resource development. The implementation of this policy has generated diverse public responses expressed through social media platforms, particularly YouTube. This study aims to analyze public sentiment toward the Free Nutritious Meal Program and to compare the performance of Logistic Regression and Support Vector Machine algorithms in multiclass sentiment classification. A total of 3,920 Indonesian-language YouTube comments were collected and processed through text preprocessing stages, including case folding, tokenization, stop word removal, and stemming. Sentiment labeling was conducted using a lexicon-based approach, and feature representation was generated using the Term Frequency–Inverse Document Frequency method. The dataset was divided into training and testing sets using an 80:20 ratio. Model performance was evaluated using accuracy, precision, recall, F1-score, and confusion matrix analysis. The results indicate that positive sentiment dominates public opinion. Although both algorithms achieved similar accuracy (0.79), Support Vector Machine demonstrated more balanced recall and F1-score across minority classes, indicating stronger robustness in handling imbalanced high-dimensional text data. These findings highlight the effectiveness of the Support Vector Machine algorithm in digital public policy evaluation through social media–based sentiment analysis.]]>
Copyrights © 2026
