<![CDATA[Academic burnout is a condition of physical, emotional, and mental exhaustion experienced by students due to continuous academic pressure. In addition to academic burnout, students may also experience religious burnout, which can reduce their participation in religious activities at school. At MTsN Tanjungbalai, the identification of student burnout risk is still conducted manually by counseling teachers, making the process subjective and less effective. This study aims to classify students based on the risk level of academic and religious burnout using the K-Means clustering algorithm. The research method applies a data mining approach with clustering techniques using student academic scores, religious scores, and learning activity data as variables. The system is designed and implemented as a web-based application to support the clustering process. The results show that the K-Means method is able to group students into several clusters representing different burnout risk levels. The developed system assists teachers in identifying students who require early attention and provides data-based information to support decision-making in student guidance and monitoring.]]>
Copyrights © 2026
