Customer Satisfaction Analysis Through Review Sentiment Using the Naive Bayes Algorithm

Abstract

The advancement of digital technology has resulted in the generation of vast amounts of data by active internet users, creating opportunities for businesses to understand customer perceptions through sentiment analysis. This study focuses on analyzing customer sentiment toward MSMEs selling on the Tokopedia platform using the Naïve Bayes algorithm and Net Promoter Score (NPS) to measure customer satisfaction. The findings show that 75.69% of customer sentiments are classified as positive, 11.08% as neutral, and 13.23% as negative. The Multinomial Naïve Bayes model achieves an accuracy level of 80%, with precision, recall, and F1-score also reaching 80%. Furthermore, the calculated NPS value of 62.46% indicates that the majority of customers are satisfied with the products and services provided by MSMEs on the Tokopedia platform.