Prediction of Elementary School Students' Mental Health using Decision Tree Algorithm with K-Fold Cross-Validation in Bone Bolango Regency, Gorontalo Province

Abstract

Mental health is a fundamental component of the World Health Organization's definition of health, encompassing not only freedom from illness but also well-being in physical, mental, and social dimensions. In today's modern society, mental health has become a paramount issue, as its soundness enables individuals to realize their own potential, cope with normal life pressures, work productively, and contribute effectively to their communities. In Indonesia, mental health-related challenges are associated with the absence of a reliable mental health detection tool. Conversely, abroad, there has been a substantial amount of research focused on innovative technology-based mental health detection using Machine Learning. This study aims to predict mental health using the Social Emotional Health Survey-Secondary (SEHS-S) as the evaluation criterion for prediction through Machine Learning. The Decision Tree algorithm is employed, and the prediction model is tested using K-Fold Cross-Validation, resulting in 8 folds with an accuracy rate of 78.61%.