ANALISIS SENTIMEN ULASAN APLIKASI SIREKAP MENGGUNAKAN ALGORITMA SUPPORT VECTOR MACHINE

Abstract

SIREKAP is the official application of the General Election Commission (KPU) used for digital vote tabulation in the 2024 elections. Since its release on the Google Play Store, the application has received various responses from users, ranging from praise to complaints. This study aims to analyze user sentiment toward the SIREKAP application by applying the Support Vector Machine (SVM) algorithm. The data analyzed consists of 15,000 Indonesian-language reviews obtained through web scraping techniques. The research process includes text preprocessing (cleaning, tokenizing, and stemming), sentiment labeling into positive, negative, and neutral categories, and training the SVM model with a linear kernel. Model performance evaluation was conducted using a confusion matrix based on accuracy, precision, and recall metrics. The results showed that the SVM model was able to classify sentiment with high accuracy, reaching 99%. This study provides an overview of public perception of the SIREKAP application and can serve as evaluation material for developers and election organizers in the future.