The performance of the Football Association of Indonesia (PSSI) often receives public scrutiny, especially from football supporters. The dynamics of Indonesian football, which are frequently colored by controversy, have generated a large number of opinions on social media. This study aims to analyze the sentiment of football supporters on social media regarding PSSI’s performance using the K-Nearest Neighbor (KNN) method. The research data were collected from Twitter through a crawling process, with word weighting performed using the TF-IDF method, while the KNN model was tested with the parameter value of k = 3. The results show that the K-Nearest Neighbor (KNN) model achieved an accuracy of 93.5%, with a precision of 63.2%, recall of 52.9%, and an f1-score of 56.5%. However, the model’s performance was influenced by data imbalance, where neutral sentiment comments were far more dominant than positive or negative ones. The sentiment distribution indicates that public opinion on social media was largely neutral, while the proportion of positive and negative sentiments was relatively smaller. These findings suggest that although criticisms of PSSI’s performance were quite prevalent, most supporters tended to remain neutral in expressing their opinions. Keywords: Sentiment Analysis, K-Nearest Neighbor, PSSI, Twitter
Ginting et al. (Wed,) studied this question.