The This research aims to analyze public sentiment toward the free meal program by utilizing the Naive Bayes Classifier (NBC) algorithm. The background of this research is based on the high public interaction on social media regarding this policy, thus requiring an analysis method that can effectively classify opinions into positive and negative sentiments. Data was collected from public posts on social media, followed by a text preprocessing stage, including data cleaning, tokenizing, stopword removal, and stemming. After that, the data was analyzed using the NBC algorithm to obtain sentiment classification. The research results show that the NBC model is capable of performing sentiment classification with an accuracy of 72%, precision of 84%, recall of 72%, and f-measure of 72%. These findings indicate that the majority of public opinion tends to be positive towards the free meal program, although there are still some negative opinions highlighting weaknesses in the policy's implementation. Overall, this research contributes by providing an objective picture of public perception through a machine learning approach. Moreover, this study proves that the NBC algorithm can be effectively used to analyze public opinion regarding government policies. Therefore, the results of this research are expected to serve as a reference in decision-making and policy evaluation in the future.
Anggreny et al. (Sat,) studied this question.