<![CDATA[PLN Mobile is a digital innovation developed by PT PLN (Persero) to provide electricity services through mobile devices. Many users submit their complaints and reviews on the Google Play Store. This study aims to analyze user sentiment towards the PLN Mobile application using three classification methods: Naïve Bayes, Random Forest, and Support Vector Machine (SVM). A total of 19,870 reviews that have gone through the preprocessing stage were analyzed in this study. Model performance was evaluated using accuracy, precision, recall, and F1-score metrics. The SMOTE technique was applied to address the imbalance of sentiment classes. The results showed that before the implementation of SMOTE, SVM had the best performance with an accuracy of 92%, followed by Random Forest 79%, and Naïve Bayes 62%. After the implementation of SMOTE, SVM performance increased to 95%, Random Forest to 85%, while Naïve Bayes remained at 62%. Other evaluation metrics such as recall and F1-score also showed significant improvements after the implementation of SMOTE, especially for negative and neutral sentiments. These results show that SMOTE is able to improve the accuracy and balance of model performance, as well as provide important insights into public perception of the PLN Mobile application.]]>
Copyrights © 2025
