IMPLEMENTASI ALGORITMA NAÏVE BAYES PADA SENTIMEN PUBLIK TERHADAP SOLUSI MENGHADAPI RESESI DI INDONESIA

Abstract

A recession is a condition in which economic activity declines significantly, characterized by a weakening Gross Domestic Product, decreasing household income, and rising unemployment rates. This condition triggers diverse public opinions, prompting this study to analyze public sentiment toward proposed solutions for addressing a potential recession in Indonesia through YouTube comments. A total of 1,204 comments were collected via web scraping and processed through several preprocessing stages, including cleansing, normalization, tokenization, stopword removal, and stemming. The cleaned data were then converted into numerical representation using TF-IDF and classified using the Naïve Bayes algorithm. Evaluation was carried out using accuracy, precision, recall, F1-score, and confusion matrix metrics. The results show that the model performed well, with evaluation scores ranging from 0.81 to 0.82 and a majority of predictions being correct. The sentiment analysis also revealed a dominance of negative comments, approximately 700 comments, while 504 comments were categorized as positive. These findings demonstrate that Naïve Bayes is effective in classifying public opinions related to recession issues and can serve as a foundation for further studies in the field of digital economic analysis.