Claim Missing Document
Check
Articles

Found 1 Documents
Search

Penerapan Klasifikasi Algoritma C4.5 Dan Algoritma C5.0 Untuk Mengetahui Tingkat Kepuasan Mahasiswa Terhadap Website Sistem Informasi Terpadu Layanan Program Studi (SIPLO) Nurfitrayani Nurfitrayani; Islamiyah Islamiyah; Amin Padmo Azam Masa
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 7, No 4 (2023): Oktober 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v7i4.6433

Abstract

Integrated Information System for Study Program Services (SIPLO) is a website-based information system for academic services at the study program level, specifically designed for the Information Systems Study Program at Mulawarman University. Despite containing information that supports lectures, SIPLO's features and information have not met students' satisfaction, as indicated by data collected through interviews. Therefore, the objective of this study was to determine the level of student satisfaction with the SIPLO website.This study employed a data mining technique using the classification methods of the C4.5 algorithm and the C5.0 algorithm. The PIECES indicators, which include performance, information, economy, control, efficiency, and service, were used as attributes in the data mining application. The data utilized in the study consisted of questionnaires distributed to 182 students from the Information Systems Study Program at Mulawarman University in 2019, 2020, and 2021. The data was divided into a 80% training data and a 20% test data ratio. The research findings using the C4.5 algorithm revealed that the variables influencing student satisfaction are performance, control, information, efficiency, and service. Meanwhile, the C5.0 algorithm identified control, performance, efficiency, information, and service as the influential variables. Both algorithms yielded an accuracy value of 91.89%, precision value of 93.75%, recall value of 96.77%, F1-Score value of 95.24%, and an AUC value of 0.8172. These results indicate a good classification performance.