This study was motivated by the large volume of user reviews for the DANA application on the Google Play Store, which contain diverse opinions regarding user experiences. While these reviews offer insights into user satisfaction and perceptions, systematic analysis is required to identify the underlying sentiments. This research aims to classify DANA user reviews into positive, negative, and neutral sentiment categories using the Support Vector Machine (SVM) algorithm. The dataset was sourced from the "DANA Sentiment Analysis from Indonesian Play Store" dataset, comprising 50,000 reviews, from which a subset of 1,500 reviews was selected using stratified sampling. The research process involved text preprocessing, TF-IDF feature weighting, data splitting, and sentiment classification using SVM with a linear kernel. Model performance was evaluated using a confusion matrix, accuracy, precision, recall, and F1-score. The results indicate that the SVM model achieved an accuracy of 82.00%, demonstrating the method's effectiveness in classifying the sentiment of DANA user reviews. These findings can serve as supporting information for identifying user responses and evaluating the user experience with the DANA application.
Copyrights © 2026