Analisis Sentimen Komentar Tik Tok terhadap Program Makan Bergizi Gratis (MBG) Menggunakan Algoritma Support Vector Machine (SVM)

Abstract

The Free Nutritious Meal Program (MBG) is a government initiative designed to improve community nutrition, particularly among students, toddlers, pregnant women, and breastfeeding mothers. Public responses to this policy have been widely expressed through social media platforms, including TikTok, where comments are often brief, informal, and unstructured. This study aims to classify public sentiment toward the MBG program into positive, negative, and neutral categories using the Support Vector Machine (SVM) algorithm and to evaluate the model’s performance. Data were collected through TikTok comment crawling techniques, resulting in 2,777 comments, of which 2,602 were retained after data cleaning. The preprocessing stages included text cleaning, case folding, normalization, tokenization, stopword removal, and stemming using the Sastrawi library. The dataset was divided into training and testing data with an 80:20 ratio, followed by TF-IDF feature extraction and SVM-based classification. Model performance was evaluated using accuracy, precision, recall, F1-score, and a confusion matrix. The results indicate that the SVM algorithm effectively classified public sentiment regarding the MBG program and successfully identified sentiment distribution patterns. These findings provide valuable insights into public perceptions of the program and contribute to the development of machine learning-based sentiment analysis for public policy evaluation in Indonesia.