Perbandingan Algoritma C4.5 Dan Naïve Bayes Untuk Mengukur Tingkat Kepuasan Mahasiswa Dalam Penggunaan Edlink

The Faculty of Computer Science, Lancang Kuning University, as a private university in the city of Pekanbaru, uses the Sevima Edlink platform as a media for academic information systems and online learning. According to some students, there are still some obstacles encountered in understanding, using and functioning this edlink application. The purpose of this study was to measure the level of satisfaction of students of the Faculty of Computer Science in using Edlink using the C4.5 and Naïve Bayes algorithms. To measure the level of accuracy of the C4.5 and Naïve Bayes algorithms in order to measure the level of student satisfaction, the indicators used are the Servqual testing model, namely Tangible, Reability, Responsiveness, Assurance, and Empathy. Based on the level of accuracy of the two methods. In the dataset used there were 91 student respondents who had filled out the questionnaire. From the questionnaire data, it was then processed using both methods and 9 comparisons of the different Training Data and Testing Data were carried out. In general, students are satisfied and understand the use of the edlink application. This satisfaction was tested using the C4.5 Decision Tree Algorithm and the Naïve Bayes Classifier. Based on the comparison that has been carried out using the C4.5 Decision Tree Algorithm, it produces an average accuracy value of 77.78%, which is slightly more accurate than the Naïve Bayes Classifier which produces an average accuracy value of 71.11%.