<![CDATA[The rapid growth of social media has made platforms such as TikTok and Instagram primary channels for the public to express opinions on various public issues, including the Free Nutritious Meal Program (MBG). The large volume of user-generated comments makes manual analysis inefficient, thereby requiring sentiment analysis approaches based on machine learning. This study aims to analyze public sentiment toward the MBG program and to compare the performance of Support Vector Machine (SVM) and Naive Bayes (NB) methods in classifying sentiments into positive, negative, and neutral categories. The dataset consists of 6,001 comments collected from TikTok and Instagram through a web scraping process using Apify and Python. The research stages include data collection, text preprocessing, feature extraction, model training, and evaluation using a confusion matrix with accuracy, precision, recall, and F1-score metrics. The results of this study are expected to provide a comparison of the performance of SVM and Naive Bayes algorithms as well as an overview of public opinion trends regarding the MBG program on social media.]]>
Copyrights © 2026
