Analisis Sentimen Publik Terhadap Kontroversi Ruu Tni Menggunakan Metode K-Nearest Neighbors

The controversy surrounding the Indonesian National Armed Forces Bill (RUU TNI) has generated significant public discourse across social media platforms such as X, TikTok, and YouTube. The unstructured nature of user comments, the frequent use of informal language, and the diversity of political terminology present substantial challenges for conducting systematic sentiment analysis. This study aims to classify public sentiment toward the RUU TNI issue using the K-Nearest Neighbors (KNN) method and to evaluate the model’s performance quantitatively. The dataset consists of 12,000 comments collected through a web scraping technique. The data were processed through several preprocessing stages, including cleaning, case folding, normalization, tokenization, stopword removal, stemming, and the integration of a political lexicon to enhance contextual representation of political terms. Subsequently, the text data were transformed using Term Frequency–Inverse Document Frequency (TF-IDF) weighting before being classified. Model evaluation was conducted using a confusion matrix and classification report. The results indicate that the KNN model achieved an accuracy of 90%, a precision of 83.33%, a recall of 100%, and an F1-score of 90.9%. These findings demonstrate that the model provides a balanced and reliable performance in classifying sentiment. Therefore, the KNN method, supported by political lexicon-based preprocessing, is proven to be effective and relevant for sentiment analysis in complex socio-political issues.