Performa Support Vector Machine (SVN) Dan Random Forest Untuk Klasifikasi Sentimen Ulasan Aplikasi elSantri

Supri Arrohman (Universitas Ibrahimy)
Zaehol Fatah (Universitas Ibrahimy)
Ahmad Homaidi (Universitas Ibrahimy)

Jurnal Inovasi Pendidikan dan Teknologi Informasi (JIPTI)
Vol. 7 No. 2 (2026): Jurnal Inovasi Pendidikan dan Teknologi Informasi (JIPTI)

Abstract The advancement of digital technology has encouraged the use of mobile applications in Islamic boarding school administrative services, one of which is the elSantri application. User reviews indicate several issues related to application performance, making sentiment analysis necessary to understand user opinions. This study aims to analyze user sentiments toward the elSantri application and compare the performance of Support Vector Machine (SVM) and Random Forest algorithms. The study employed the Knowledge Discovery in Database (KDD) method using 383 reviews collected from the Google Play Store. The research stages included preprocessing, TF-IDF weighting, sentiment classification, and evaluation using a confusion matrix. The results show that SVM achieved an accuracy of 83.12%, while Random Forest achieved 77.92%. The novelty of this study lies in the implementation and comparison of both algorithms on reviews of the elSantri application, a digital Islamic boarding school administration application. Keywords: Sentiment Analysis; Support Vector Machine; Random Forest; TF-IDF; elSantri.