Comparasion of Support Vector Machine and Decision Tree Methods in Sentiment Analysis of Social Media X User Toward the Free Nutritious Meal Program

Olinda Nathaniel Mendrofa (Universitas Prima Indonesia)
Deva Angriani (Universitas Prima Indonesia)
Elvis Sastra Ompusunggu (Universitas Prima Indonesia)

Formosa Journal of Computer and Information Science
Vol. 5 No. 2 (2026): August 2026

The research stages include a preprocessing process consisting of cleaning, case folding, tokenizing, normalization, stopword removal, and stemming. Furthermore, the TF-IDF method is used to extract text features so that the data can be represented in numerical form. The dataset was then divided into training data and test data with an 80:20 ratio. The model evaluation was carried out using a confusion matrix by paying attention to the values of accuracy, precision, recall, and F1-Score. The results showed that the Support Vector Machine algorithm had better performance than Decision Tree in classifying the sentiment of social media users X towards the Free Nutritious Meal Program. The SVM algorithm obtained an accuracy score of 75.42%, precision of 74.65%, recall of 75.42%, and F1-Score of 74.96%. Meanwhile, the Decision Tree algorithm produced an accuracy value of 72.08%, precision of 73.33%, recall of 72.08%, and F1-Score of 72.59%.