Analisis Sentimen Opini Masyarakat Terhadap Program Makan Bergizi Gratis di Media Sosial X

Abstract

The Free Nutritious Meals (MBG) Program is a government policy that has generated diverse public responses, particularly on the social media platform X. Given the large volume of public opinions, sentiment analysis is needed to identify public sentiment toward the program. This study aims to classify sentiment using the Support Vector Machine method and analyze public opinion regarding the MBG Program. The study uses data collected from the social media platform X. The research methodology consists of data collection, text preprocessing (including case folding, cleaning, tokenizing, stopword removal, and stemming), data labeling using the InSet lexicon, and term weighting using Term Frequency–Inverse Document Frequency. Sentiment classification is then performed using the Support Vector Machine method, and the model is evaluated using a confusion matrix with accuracy, precision, recall, and F1-score metrics. In addition, opinion mining is conducted to identify the dominant words that shape public opinion. The results show that the Support Vector Machine model achieved an accuracy of 98.26%, with precision, recall, and F1-score values above 97% for both classes, indicating excellent classification performance. The sentiment analysis reveals that public opinion regarding the MBG Program is dominated by negative sentiment (57.91%), while positive sentiment accounts for 42.09%. Positive sentiment is characterized by perceptions of the program's benefits for children's nutrition, educational quality, and support for the government. In contrast, negative sentiment is characterized by concerns about food safety, the quality of program implementation, and calls for further evaluation of the program. The study concludes that the Support Vector Machine method is effective for classifying public sentiment regarding the MBG Program. Furthermore, the findings indicate that public opinion on X is predominantly negative, reflecting public perceptions of the program's implementation