Skip to content
Open access

Low-dimensional burnout risk classification in engineering students: the role of demand-recovery interaction features

Nov 2026 · Frontiers in Psychology · Vol 17 · 0 citations · 23 references

Abstract

Student burnout is a rapidly growing concern, with prior research linking its development to a wide range of psychological, behavioral, and contextual factors. Machine learning approaches have recently shown strong predictive performance for identifying burnout, but typically rely on high-dimensional datasets impractical for real-world use. Whether burnout can be reliably identified from a minimal set of variables remains underexplored. This study addresses that gap using a low-dimensional predictive framework in undergraduate engineering students. Grounded in Conservation of Resources theory, three classifiers (Logistic Regression, Random Forest, Gradient Boosting) were evaluated across three feature configurations (Raw: all nine unengineered base predictors, including academic, demographic, sleep, and physical activity variables; Engineered: four demand–recovery interaction features; Full: Raw combined with Engineered) to test whether burnout reflects academic load alone or an imbalance between demand and recovery capacity. The Full configuration performed best: Logistic Regression and Random Forest exceeded a matched permutation-based null (Global MCC = 0.173 and 0.190, respectively, p  < 0.05), while Gradient Boosting did not reach significance (MCC = 0.126, p  = 0.066). Across 50 alternative fold splits, however, mean Global MCC for the Full configuration was lower for each classifier (Logistic Regression 0.09, Random Forest 0.16, Gradient Boosting 0.11), indicating that the primary-split estimates are upper-range. In addition, adding engineered features to Raw predictors did not produce a statistically distinguishable improvement in Global MCC for any classifier. Moderate Risk classification remained difficult across all classifiers and configurations, with most confidence intervals crossing zero. Permutation importance identified Workload-Sleep Strain as the most influential predictor in the Random Forest model, suggesting the engineered features capture meaningful behavioral patterns. However, because these variables are deterministic transformations of the raw predictors, their incremental contribution could not be confirmed statistically. These results offer preliminary evidence that a small set of sleep, activity, workload, and engineered variables carries predictive signal for burnout risk above chance.

Read PDF

Similar papers

Review Open access Oct 2026

Development of a Machine-Learning-Based Predictive Model for Burnout Among Senior High School Teachers

Teacher burnout is a persistent problem characterized by psychological exhaustion and occupational stress, posing serious constraints on teachers’ professional development, the improvement of teaching quality, and the stable functioning of the educational ecosystem. Conventional questionnaire-based surveys, which domin...

Jun Peng, Yi-Lin Jiang, Xiao-Yu Liu et al. · 0 citations
Open access Sep 2026

Construction of an Early Warning Model for Academic Burnout among High School Students Based on Learning Behaviour Data

An explainable machine-learning approach to identifying cases of academic burnout among high school students based on their observable learning behaviors is suggested, using a publicly accessible dataset that includes information about 649 adolescents and contains no validated burnout measurement.

Tian-Ge Xiang · 0 citations
Review Open access Oct 2026

Assessing Employee Wellbeing and Retention Risk: An Integrated and Explainable Machine-Learning Decision-Support Framework Using Validated Psychometric Measures

Employee burnout, poor work-life balance, and voluntary turnover are costly problems, yet they are usually studied separately and inferred from administrative records rather than measured directly. This study models the three together, explains them transparently, and translates them into decision support within one fr...

A. J, Kalai Lakshmi Tr, Bharathi R et al. · 0 citations
Open access Sep 2026

Model Selection Analysis for Predicting Students Mental Health from Academic and Psychological Variables

This paper proposes a complete model selection analysis in order to predict mental health index based on 15 predictor variables taken from student mental health and burnout dataset (N = 2,549). The approach uses the stepwise regression method, which includes forward, backward and bidirectional selection procedures alon...

A. Ismail · 0 citations
Open access Oct 2026

Behavioral, Life Style and Psychological Predictors of Adolescent Depression: A Machine Learning Approach

Adolescent depression has one of the major public health concerns due to its negative impacts on psychological well-being, academic success, and social functioning. Proactive detection of adolescent at risk is essential for timely support and assistance; however, conventional statistical methods may not adequately capt...

Joy Deb, Debajit Biswas, Subham Roy · 0 citations
Conference Open access Sep 2026

SLP-LR: A Predictive Analytics Approach for Mental Stress Detection among University Students

Student stress can adversely affect academic performance and mental well-being, creating a need for scalable support tools in higher education. This study investigates multiclass student stress classification using a dataset of 2,028 Bangladeshi university-student responses containing demographic variables and ten acad...

Abhiram Chowdary Ravella, Bala Manindra Tatineni, Mohith Chowdary Virigineni et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.