SENTIMENT ANALYSIS OF JAKLINGKO APP REVIEWS USING MACHINE LEARNING AND LSTM

Application-based transportation services have rapidly developed in recent years, with various studies indicating that service quality and user experience play a crucial role in the adoption of this technology. Previous research has analyzed user satisfaction with digital transportation applications, highlighting factors such as ease of use, service reliability, and the effectiveness of fare systems. This study aims to analyze user sentiment toward the JakLingko application to assess satisfaction levels and identify aspects that need improvement. Utilizing a dataset of 200 user reviews, this research applies data preprocessing techniques to clean and organize the information before performing sentiment classification. The machine learning models used include Naïve Bayes, Random Forest, Support Vector Machine, Logistic Regression, Decision Tree, and Long Short-Term Memory (LSTM), categorizing sentiment into positive, negative, and neutral. The analysis results indicate a dominance of negative sentiment in user reviews, reflecting a significant level of dissatisfaction with the application. This highlights major challenges in the implementation of transportation applications, potentially affecting public adoption and trust in the service. Therefore, besides providing insights into user perceptions, this study also proposes improvement strategies aimed at enhancing features and the overall user experience. Given the high proportion of negative sentiment, this research emphasizes the importance of improving the accuracy of sentiment analysis models to generate deeper and more precise insights. These findings can serve as a foundation for designing policies and strategies to improve application-based transportation services, ultimately enhancing service quality and expanding user adoption.