Analysis of Student Mental Health Dataset Using Mining Techniques

Abstract

This study utilizes a decision tree model in RapidMiner to analyze a dataset from Kaggle, comprising 200 student records. Among these, 70 students reported mental health issues, while 130 did not. Strikingly, a significant majority of 58 out of the 70 students with mental health concerns do not seek assistance from professionals. This study underscores the pressing issue of underutilization of mental health services among students and offers practical solutions, such as enhancing awareness and education, improving access to mental health services, providing peer support, and addressing underlying issues. The research design includes data collection methods that maintained ethical standards and the decision tree model's application for analysis. This study's contribution lies in its identification of the prevalence of students with mental health issues who do not seek help and the proposed solutions to address this critical issue.