<![CDATA[This study aims to classify public sentiment toward the Kartu Indonesia Pintar Kuliah (KIP-K) program based on comments collected from Twitter and Instagram social media platforms. The dataset consists of 3,214 public comments gathered via web scraping using relevant keywords during the period of January 2024 to May 2025. Data processing stages include preprocessing (cleaning, case folding, tokenizing, stopword removal, and stemming), automatic sentiment labeling using the InSet (Indonesian Sentiment Lexicon) lexicon-based approach, and feature extraction using TF-IDF. Two classification methods were compared: Naïve Bayes and Support Vector Machine (SVM). The evaluation results show that SVM outperforms Naïve Bayes in all metrics, achieving 80% accuracy with macro precision, recall, and F1-score of 0.81, 0.80, and 0.80, respectively. In contrast, Naïve Bayes achieved 60% accuracy with a macro score of 0.61. This study indicates that the majority of public sentiment toward KIP-K is positive, although there are significant proportions of neutral and negative sentiments related to targeting inaccuracies and fund misuse.]]>
Copyrights © 2026
