Sentiment analysis towards naturalization of Indonesian National Team Players on social media x using the Naive Bayes method

Abstract

This study analyzes public sentiment toward naturalized players in the Indonesian National Team on social media platform X (formerly Twitter) using the Naïve Bayes method. Data were collected via Python's snscrape library through web crawling, encompassing 700 tweets from January 2023 to May 2024. The research methodology included data preprocessing (cleaning, case folding, tokenizing, stopword removal, and stemming), feature extraction with TF-IDF (Term Frequency-Inverse Document Frequency), and sentiment classification. Results revealed a dominant negative sentiment (87.5%) compared to positive sentiment (12.5%), with a model accuracy of 88%. The most frequent keyword, "main" (play), reflected public focus on player performance.The study contributes to the field in three key aspects: (1) It addresses a gap in literature by specifically examining sentiment toward naturalization policies in Indonesian football using social media data; (2) It demonstrates the effectiveness of Naïve Bayes in handling informal Indonesian language, achieving high accuracy despite linguistic complexities; (3) It provides actionable insights for policymakers, highlighting the need for greater transparency in naturalization processes. Limitations include potential bias due to imbalanced data and challenges in interpreting sarcasm. Recommendations for future research include expanding datasets to multiple platforms and testing advanced models like BERT for improved contextual analysis.