PUBLIC SENTIMENT ANALYSIS OF THE ANTAM GOLD CASE ON SOCIAL MEDIA X USING THE SUPPORT VECTOR MACHINE (SVM) METHOD

Abstract

The development of social media, especially X (Twitter), has made it an important source for observing public opinion. One of the issues widely discussed is the Antam gold case related to the alleged misuse of official stamps and the circulation of illegal gold. This study analyzes public sentiment toward this issue by classifying tweets into positive, negative, and neutral categories. Data were collected through crawling using the keyword “kasus emas antam” during the period March 1–May 7, 2025, resulting in 716 tweets. The research process includes preprocessing, feature extraction using N-gram and TF-IDF, and classification using Support Vector Machine (SVM). Evaluation was carried out using a confusion matrix to calculate accuracy, precision, recall, and F1-score. The results show that the SVM model achieved an accuracy of 85%, precision of 91%, recall of 78%, and an F1-score of 80%, indicating good performance in classifying sentiment. This research is expected to provide an overview of public perception and serve as a reference in the application of sentiment analysis on other social issues.