Prediksi Tingkat Kepuasan Pengguna Aplikasi Pojokcat dalam Pembelajaran Online Menggunakan Algoritma Naïve Bayes

Technological developments in education have encouraged the use of online learning applications, one of which is PojokCAT, used by prospective students (casis) to prepare for the National Police selection exam. However, the lack of a systematic evaluation of user satisfaction levels has led to questions about the extent to which this application is able to meet learning needs. This study aims to predict the level of satisfaction of PojokCAT application users using the Naïve Bayes algorithm. Data were obtained from a courage questionnaire completed by 384 active respondents using the application. The process analysis included preprocessing, data sharing, model training, and performance classification evaluation. The results showed that the Naïve Bayes algorithm was able to predict satisfaction levels with an accuracy of 91.38%. The precision value reached 86.67%, recall was 90.70%, and AUC was 0.971, indicating excellent classification performance. In general, this indicates that PojokCAT has been able to meet the needs of its users. However, there are still certain aspects that require further improvement. These findings indicate that the Naïve Bayes algorithm is effective for classifying user satisfaction levels in online learning applications.