Student depression screening based on the optimum data balancing and random forest

Adnan, M. Sayyidul, Santoso, Irwan Budi ORCID: https://orcid.org/0000-0001-5586-9035 and Crysdian, Cahyo ORCID: https://orcid.org/0000-0002-7488-6217 (2026) Student depression screening based on the optimum data balancing and random forest. JURTEKSI (jurnal Teknologi dan Sistem Informasi), 12 (2). 309 -316. ISSN 2550-0201

Preview

Text 29394.pdf - Published Version Available under License Creative Commons Attribution Share Alike. Download (473kB) | Preview

Abstract

Mental health issues, particularly depression among young adult university students, are often detected late due to stigma and reluctance to seek medical consultation. The objective of this study is to develop an early screening model employing machine learning techniques, specifically the random forest algorithm, on a dataset of 268 students (aged 17-29 years; consisting of 98 males and 170 females) within a multicultural educational setting. The principal challenges associated with this dataset are class imbalance and the potential for data leakage from clinical scores. This study implements a rigorous feature selection approach that involves the elimination of depression score features and the utilization of the Synthetic Minority Oversampling Technique (SMOTE) to balance the training data distribution. Furthermore, a Threshold Tuning strategy is employed to prioritize detection sensitivity (Recall). The findings indicate that reducing the decision threshold to an optimal value of 0.25 led to a substantial enhancement in the recall value, increasing it from 36% (baseline) to 77%. A feature importance analysis was conducted, the results of which indicated that Total Social Connectedness (ToSC) is the most dominant predictor. In summary, the present study corroborates the notion that optimizing sensitivity through threshold tuning is of paramount importance for medical screening. Furthermore, social isolation factors emerge as more significant indicators of depression risk than demographic attributes.

Item Type:	Journal Article
Keywords:	data mining; depression; imbalanced data; random forest; smote; threshold tuning
Subjects:	08 INFORMATION AND COMPUTING SCIENCES > 0801 Artificial Intelligence and Image Processing > 080199 Artificial Intelligence and Image Processing not elsewhere classified
Divisions:	Faculty of Technology > Department of Informatics Engineering
Depositing User:	irwan budi santoso
Date Deposited:	29 Oct 2026 10:09

Downloads

Origin of downloads

Actions (login required)

View Item