Protecting Student Mental Health with a Context-Aware Machine Learning Framework for Stress Monitoring

TL;DR

This paper presents a novel context-aware machine learning framework that effectively classifies student stress levels using diverse data sources, outperforming previous benchmarks and enabling timely mental health interventions in academic settings.

Contribution

It introduces a comprehensive six-stage pipeline with ensemble strategies for stress classification, integrating psychological, academic, environmental, and social factors.

Findings

Achieved 93.09% accuracy with weighted voting on one dataset.

Achieved 99.53% accuracy with stacking on another dataset.

Outperformed existing benchmarks in student stress classification.

Abstract

Student mental health is an increasing concern in academic institutions, where stress can severely impact well-being and academic performance. Traditional assessment methods rely on subjective surveys and periodic evaluations, offering limited value for timely intervention. This paper introduces a context-aware machine learning framework for classifying student stress using two complementary survey-based datasets covering psychological, academic, environmental, and social factors. The framework follows a six-stage pipeline involving preprocessing, feature selection (SelectKBest, RFECV), dimensionality reduction (PCA), and training with six base classifiers: SVM, Random Forest, Gradient Boosting, XGBoost, AdaBoost, and Bagging. To enhance performance, we implement ensemble strategies, including hard voting, soft voting, weighted voting, and stacking. Our best models achieve 93.09% accuracy with weighted hard voting on the Student Stress Factors dataset and 99.53% with stacking on the Stress and Well-being dataset, surpassing previous benchmarks. These results highlight the potential of context-integrated, data-driven systems for early stress detection and underscore their applicability in real-world academic settings to support student well-being.