Implementasi Support Vector Machine Dalam Analisis Sentimen Netizen Terhadap Program Makan Bergizi Gratis

The Free Nutritious Meal Program (MBG) is a government policy that has generated various responses from the public on social media, particularly on X and TikTok. This study aims to apply the Support Vector Machine (SVM) algorithm to
classify netizens' sentiments towards the Free Nutritious Meal Program into two categories, namely positive and negative. The research data was obtained from scraping 7,354 comments on the X and TikTok platforms. The research method used the Knowledge Discovery in Database (KDD) approach with word weighting using the Term Frequency–Inverse Document Frequency (TF-IDF) method. The test results showed that the SVM model produced an accuracy rate of 82% on the X platform and 88% on the TikTok platform, which was influenced by the imbalance in data distribution. Meanwhile, testing on combined data with a more balanced sentiment distribution achieved an accuracy of 83% with more stable classification
performance. These findings indicate that the SVM algorithm is effective and works more consistently in analyzing netizens' sentiments towards the Free Nutritious Meals Program.