Analisis Sentimen Ulasan Aplikasi Cek Bansos Pada Google Play Store Menggunakan Metode Support Vector Machine

The Cek Bansos application is a digital solution launched by the Ministry of Social Affairs (Kemensos) to help people access and manage social assistance programs easily. However, many users complain about various obstacles when
using the social assistance check application, especially in the registration and login process. Thus, many people feel dissatisfied with the system that has been provided by the government. Therefore, this research aims to build a sentiment analysis model to identify problems faced by users. To identify these problems, this research uses the Support Vector Machine algorithm and reviews from the Google
Play Store. This research will classify user reviews into positive and negative sentiments and classify the need to discuss features and not discuss features. The results of this study show that the accuracy of the model for sentiment reaches 83%, while the accuracy for needs classification is 94%. So that this value has a good value for classifying user review data for the social assistance check application. In addition, this research can be used as a reference for developers to improve and update the social assistance check application so that people have no difficulty in using the services in the social assistance check application.