<![CDATA[PT Kereta Api Indonesia (Persero), a State-Owned Enterprise (SOE) in the railway sector, holds an important responsibility in providing efficient services. To enhance their services, they introduced the application "Access by KAI.” Although this application represents a technological innovation, it often falls short of users' expectations due to existing shortcomings. Therefore, this study proposes the use of sentiment analysis to gauge users' perspectives on the "Access by KAI” application. By applying Support Vector Machine (SVM) and Random Forest algorithms to user review datasets, this study classifies user sentiments into three categories: positive, neutral and negative, and compares the performance of these two algorithms. The results of this study offer valuable insights into users' attitudes towards the application, which can assist PT Kereta Api Indonesia in improving service quality. The classification results using the Random Forest and Support Vector Machine (SVM) algorithms, based on the factors used in this study, show varying performance. Random Forest achieved an accuracy of 86% for an 80:20 and 90:10 data ratios, and 85% for a 70:30 ratio, while SVM achieved 83% accuracy across different data ratios]]>
Copyrights © 2026
