<![CDATA[The rapid growth of digital banking applications in Indonesia requires companies to pay close attention to user perceptions and satisfaction. This research focuses on analyzing the sentiment of user reviews of the Allo Bank application obtained from the Google Play Store, applying the Support Vector Machine (SVM) algorithm combined with a Natural Language Processing (NLP) approach. A total of 5,100 reviews in the Indonesian language were collected using web scraping methods. The analysis involved several stages, including text preprocessing, term weighting with TF-IDF, sentiment classification into three categories (positive, negative, and neutral), and performance evaluation of the model. The findings reveal that most user reviews express positive sentiment, with frequently appearing words such as "easy,” "secure,” and "good.” Negative sentiments are commonly represented by words like "complicated,” "lag,” and "slow,” while neutral reviews often include expressions such as "adequate” and "okay.” The SVM model achieved strong performance, with an accuracy of 96%, precision of 97%, recall of 75%, and an F1-score of 79%, indicating high effectiveness despite limited sensitivity to minority classes. These classification results can provide valuable insights for identifying areas that need improvement or should be maintained by the application developers. Therefore, this study is expected to serve as a reference for strategic decision-making based on user feedback to enhance the quality of digital banking services.]]>
