<![CDATA[The rapid development of digital banking technology requires improvements in service quality to remain competitive in the financial industry. Seabank Indonesia is one of the widely used digital banking applications, making sentiment analysis of user reviews an essential aspect of understanding their perceptions of the provided services. This study evaluates user sentiment toward the Seabank application by implementing the Naïve Bayes algorithm to optimize service quality. The research data was obtained through a web scraping process from the Google Play Store, totalling 1,000 reviews. The Knowledge Discovery in Databases (KDD) approach was applied in the analysis, encompassing preprocessing stages such as cleaning, casefolding, tokenization, stopword removal, stemming, and Term Frequency-Inverse Document Frequency (TF-IDF) representation. The classification model was built by splitting the dataset into 70% training and 30% test data. The evaluation results indicate that the developed model achieved an accuracy of 88%, with a precision of 95%, recall of 87%, and F1-score of 91%. An analysis of all reviews revealed that 70.5% were positive, while 29.5% were negative. These findings demonstrate that the Naïve Bayes algorithm is effective in analyzing user sentiment and provides valuable insights for developers to enhance the quality of Seabank Indonesia’s services.]]>
Copyrights © 2025
