CLASSIFICATION OF COLLEGE STUDENTS' STRESS LEVELS USING THE RANDOM FOREST ALGORITHM BASED ON DASS-21

ZAHRA, RAISA INDIRA (2026) CLASSIFICATION OF COLLEGE STUDENTS' STRESS LEVELS USING THE RANDOM FOREST ALGORITHM BASED ON DASS-21. Tugas Akhir thesis, University of Technology Yogyakarta.

Text 5220411108_RAISAINDIRAZAHRA_ABSTRAK.pdf Download (138kB)

Abstract

ABSTRACT Academic stress is a psychological condition frequently experienced by college students due to heightened demands in academics, social life, and emotions. If not detected early, this issue can adversely affect both mental health and academic performance. This study aims to develop and evaluate a machine learning model using the Random Forest algorithm to predict college students' stress levels based on the Indonesian version of the Depression Anxiety Stress Scale-21 (DASS-21). Data were collected from 143 college students in Yogyakarta who completed the DASS-21 questionnaire; stress subscale scores from seven items were doubled and categorized into five levels: Normal, Mild, Moderate, Severe, and Very Severe. The data were then cleaned, labelled, normalised, and split into training and test sets (60:40) using stratified sampling. Model performance was evaluated using accuracy, macro-F1, Mean Absolute Error (MAE), and Root Mean Squared Error (RMSE). The Random Forest model achieved an accuracy of 87.93%, a macro-F1 score of 0.7047, an MAE of 0.121, and an RMSE of 0.347, with the best performance observed in the Severe (F1 = 0.9387) and Normal (F1 = 0.9230) categories. To enhance practical usability, the model was implemented in a web-based system called StressPredict, which provides real-time predictions, class probabilities, and an analytical dashboard for monitoring student populations. These findings demonstrate the effectiveness of the Random Forest algorithm for multilevel stress classification and highlight its strong potential as a digital mental health monitoring tool in higher education settings, supporting early screening and informed interventions to promote student well-being. Keywords: DASS-21, Digital Mental Health, Machine Learning, Random Forest, Student Stress

Item Type:	Thesis (Skripsi, Tugas Akhir or Kerja Praktek) (Tugas Akhir)
Subjects:	T Technology > T Technology (General) > T201 Patents. Trademarks
Divisions:	Fakultas Sains Dan Teknologi > S1 Informatika
Depositing User:	Kaprodi S1 Informatika UTY
Date Deposited:	06 May 2026 03:55
Last Modified:	06 May 2026 03:55
URI:	http://eprints.uty.ac.id/id/eprint/19793

Actions (login required)

View Item