Analisis Sentimen Ulasan Pengguna QRIS pada Aplikasi GoPay: Studi Komparatif Algoritma Support Vector Machine dan Decision Tree Berbasis TF–IDF

Erlinda Sistia Aritonang (Universitas Mercu Buana, Jakarta)
Yuwan Jumaryadi (Universitas Mercu Buana, Jakarta)

TIN: TERAPAN INFORMATIKA NUSANTARA
Vol 6 No 12 (2026): May 2026

This study aims to analyze user sentiment towards the QRIS feature in the GoPay application based on reviews on the Google Play Store and to build a sentiment classification model using a machine learning approach. A total of 20,746 reviews were collected and filtered using QRIS-related keywords, resulting in 4,347 relevant reviews. The data were manually labeled and preprocessed, then extracted using the TF–IDF method. The analysis results show a sentiment distribution consisting of 49.49% positive, 35.34% negative, and 15.18% neutral. The classification process was carried out using the Support Vector Machine (SVM) and Decision Tree algorithms. The evaluation results showed that Decision Tree achieved 79% accuracy with precision, recall, and F1-score values ​​of 79% each, while SVM produced 78% accuracy with precision of 79%, recall of 78%, and F1-score of 78%. The difference in performance between the two models was relatively small, so both had equal capabilities in sentiment classification, although Decision Tree showed slightly better metric consistency.