<![CDATA[Lalamove is a widely used application-based logistics service in Indonesia, and user reviews on the Google Play Store provide essential insights into users’ experiences and perceptions of the platform. This study applies Natural Language Processing (NLP) techniques and machine learning algorithms to process thousands of reviews efficiently and consistently. The textual data were cleaned, normalized, and converted into numerical representations using the TF-IDF method. Three classification models—Naïve Bayes, Support Vector Machine (SVM), and Random Forest—were implemented to determine sentiment tendencies. Model performance was evaluated using accuracy, precision, recall, and F1-score metrics. The findings reveal notable differences in the ability of each algorithm to recognize textual patterns, and the results can be utilized as a reference for improving the quality of Lalamove’s services based on user feedback.]]>
Copyrights © 2026
