Sentiment Analysis Mobile JKN Reviews Using SMOTE Based LSTM

• DOI: 10.22146/ijccs.101910
• Publication Date: 2025-02-14T02:33:56Z
• Authors: Ghufron Tamami; Wiwit Agus Triyanto; Syafiul Muzid
• Keywords: Sentiment Analysis

The JKN Mobile application plays an important role in providing easy and fast access to health services for JKN-KIS users. However, user reviews indicate dissatisfaction with several aspects of the application, such as login issues OTP codes, which can affect overall experience. Another challenge faced is class imbalance review dataset, performance sentiment analysis. This study uses Long Short-Term Memory (LSTM) combined Synthetic Minority Oversampling Technique (SMOTE) address imbalance. Review data was collected from Google Play Store Kaggle, then preprocessed including lemmatization, tokenization, padding. Model evaluated using accuracy, precision, recall, F1-score metrics. results showed that LSTM SMOTE achieved 88% 90% 89% F1-score. successfully improved minority although there a slight decrease accuracy compared model without SMOTE. Word cloud visualization reveals positive sentiments regarding ease use while negative areas need improvement. emphasizes importance handling imbalanced datasets produce more accurate