<![CDATA[This study aims to analyze public sentiment regarding reviews of the Grab application on the Google Play Store using the Multinomial Naive Bayes algorithm. The research process follows the KDD stages, starting from data selection, pre-processing, sentiment labeling, dataset splitting, model training, to performance evaluation. A total of 5,000 review data were collected through web scraping techniques and processed step by step using cleaning, normalization, tokenizing, stopword removal, and stemming methods. The developed Multinomial Naive Bayes model was able to classify review sentiments into positive, negative, and neutral categories with an accuracy of 69.6%. Precision and recall for negative and positive sentiments are relatively high, but the performance for neutral sentiment remains low due to imbalanced data distribution. The results of this study provide valuable insights for Grab developers to understand user perceptions and can serve as a basis for strategic decision-making to improve application service quality. Thus, Multinomial Naive Bayes has proven to be effective and efficient for sentiment analysis of Grab app reviews on the Google Play Store.Keywords: Sentiment Analysis, Multinomial Naive Bayes, Grab, Google Play Store, KDD]]>
Copyrights © 2025
