<![CDATA[This study aims to analyze public sentiment towards the Free Nutritious Food Program (MBG) based on user comments on the TikTok platform using the Support Vector Machine (SVM) algorithm. Data were collected through a scraping process, resulting in 673 comments related to the MBG program. The research stages included text pre-processing consisting of data cleaning, case folding, normalization, tokenization, stopword removal, and stemming. The data were then labeled into positive, negative, and neutral sentiment categories using a lexicon-based approach and converted into numerical features using the Term Frequency–Inverse Document Frequency (TF-IDF) method. Sentiment classification was performed using the SVM algorithm to identify public perceptions of the program. The labeling results showed that neutral sentiment dominated with 539 comments, followed by 90 positive comments and 44 negative comments. The model evaluation showed good performance, achieving an accuracy of 82.96%, a precision of 82.95%, a recall of 82.96%, and an F1-score of 76.47%. These findings indicate that SVM is effective for analyzing public sentiment on social media and can assist the government in understanding public perceptions of policy programs.]]>
Copyrights © 2026
