<![CDATA[This study develops an automated sentiment analysis system to classify Indonesian-language user reviews of the JobStreet application from the Google Play Store. It compares the performance of two machine learning algorithms, Support Vector Machine (SVM) and Naive Bayes. The review data were preprocessed through cleaning, case folding, tokenization, normalization, stopword removal, and stemming before model training and evaluation. Performance was measured using accuracy, precision, recall, and F1-score. The results show that SVM outperformed Naive Bayes, achieving 97% accuracy, 0.98 precision, 0.96 recall, and a 0.97 F1-score. In comparison, Naive Bayes achieved 89% accuracy, 0.93 precision, 0.83 recall, and a 0.86 F1-score. SVM demonstrated more balanced precision and recall across sentiment classes, indicating better classification performance. These findings suggest that SVM is more effective for Indonesian-language sentiment analysis and has strong potential for implementation in automated systems to support intelligent recommendations and improve service quality on digital recruitment platforms]]>
Copyrights © 2024
