T The increasing use of the mypertamina application has resulted in a growing number of user reviews on the google play store, containing various experiences, satisfaction levels, and complaints regarding the application. the large volume of reviews makes manual analysis inefficient, creating a need for an automated sentiment analysis system. this study aims to develop a web-based sentiment analysis system to classify mypertamina user reviews into three sentiment categories: positive, neutral, and negative, and to present the analysis results through an interactive dashboard. the data were collected through web scraping of google play store reviews and labeled based on user ratings. the data preprocessing stages consisted of basic cleaning, tokenization, normalization, stopword removal, negation handling, and stemming. feature extraction was performed using term frequency–inverse document frequency (tf-idf), while sentiment classification was conducted using the support vector machine (svm) algorithm. model performance was evaluated using a confusion matrix, accuracy, weighted precision, weighted recall, and weighted f1-score. the usability of the dashboard was evaluated using the system usability scale (sus). the results show that the model achieved an accuracy of 88.71%, weighted precision of 88.41%, weighted recall of 88.71%, and weighted f1-score of 87.30%. the streamlit-based dashboard successfully presents sentiment distribution and trends, word analysis, model evaluation, and sentiment prediction features interactively. the sus evaluation resulted in a score of 78.5, indicating good system usability. therefore, the combination of tf-idf and svm provides good performance for classifying sentiment in mypertamina user reviews, while the developed dashboard effectively presents the analysis results in an interactive form.