Twitter has become a major platform for real-time public expression, including reactions to the Indonesian national football team’s new jersey released by Erspo on January 23, 2025. The previous edition had received strong criticism, creating the need to examine how the public responded to the new design. This study aims to analyze the distribution of sentiments on Twitter and evaluate the performance of the chosen classification method. The research employs Support Vector Machine (SVM) with a linear kernel to classify Indonesian-language tweets into positive and negative categories. Data were collected through crawling and processed using text preprocessing techniques such as case folding, tokenizing, filtering, and stemming, with features extracted using Term Frequency–Inverse Document Frequency (TF-IDF). The model’s performance was assessed based on accuracy, precision, and recall. Results show that public sentiment comprised 308 positive and 437 negative tweets. The SVM model achieved an accuracy of 82.35%, with 76% precision for positive and 86% precision for negative classifications. These results indicate that public responses tended to be negative, though positive appreciation was still evident. Overall, SVM proved effective for sentiment analysis and can provide valuable insights for decision-makers and jersey developers.
Akbar et al. (Wed,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: