<![CDATA[In the rapidly evolving digital era, sentiment analysis has become crucial for understanding diverse user opinions. However, there is a gap in comparative studies on the effectiveness of machine learning methods for sentiment analysis of e-wallet applications in Indonesia. This research aims to compare the performance of Support Vector Machine (SVM) and Naive Bayes methods in sentiment analysis of user reviews for the OVO application, sourced from the Google Play Store. A total of 3,000 reviews were collected and processed through text preprocessing stages, including data cleaning, case folding, stopword removal, tokenizing, and stemming. Sentiment labeling was performed automatically using the VADER method, resulting in three categories: positive, neutral, and negative. The data was then transformed into numerical format using TF-IDF before being applied to the SVM and Naive Bayes models. Model performance was evaluated using a confusion matrix with metrics such as accuracy, precision, recall, and F1-score. The results showed that the SVM method delivered better outcomes with an accuracy of 89%, precision of 89%, recall of 89%, and F1-score of 88%, compared to the Naïve Bayes method, which achieved an accuracy of 86%, precision of 88%, recall of 86%, and F1-score of 87%. These findings can serve as a reference in selecting machine learning methods for sentiment analysis of e-wallet applications and assist OVO in improving service quality based on user feedback.]]>
Copyrights © 2025
