Sentiment Analysis of Public Opinion on PSSI Naturalization Program Based on Social Media Using the Naive Bayes Algorithm

Football is the most popular sport in Indonesia and receives tremendous support from the public. However, the player naturalization program initiated by PSSI (the Indonesian Football Association) has become an issue that has captured public attention, generating diverse opinions on social media, particularly on the Twitter platform. This study aims to analyze public sentiment toward the naturalization program by applying the Naïve Bayes classification method. The data used consists of tweets containing keywords related to PSSI naturalization, naturalized players, descendant players, national team naturalization, and overseas players for the national team. The analysis process includes several stages of data preprocessing—such as text cleaning, normalization, and stop word removal—feature extraction using TF-IDF, and sentiment classification using the Naïve Bayes algorithm to categorize opinions into positive, negative, and neutral sentiments. The Naïve Bayes model achieved an accuracy of 0.65, precision of 0.42, recall of 0.65, and an F1-score of 0.51. It performed well in classifying neutral tweets but was less effective in identifying positive and negative sentiments. Overall, the Naïve Bayes method can be utilized for sentiment analysis; however, its classification performance is not yet optimal due to the limited amount of data.