Optimising SVM models in text mining to see the sentiments and user complaints of DANA mobile application through play store reviews

Biyantoro, Arell Saverro
Prasetiyo, Budi

Journal of Student Research Exploration
Vol. 3 No. 2 (2025): July 2025

Dana is a mobile electronic wallet application available for download on Google Play Store. Users can rate and comment on this application directly through the review section on the platform. By utilizing these user reviews, research can be conducted to identify the main complaints experienced by Dana application users. This research uses Support Vector Machine (SVM) sentiment analysis to classify reviews and Latent Dirichlet Allocation (LDA) to map negative comment topics. LDA extracts several representative words or tokens that are grouped to form specific themes. The findings show that the most common sources of user complaints are related to transaction issues, premium features, and app updates. These insights can provide valuable input for developers to improve the overall quality and user experience of the Dana app.