A Machine Learning Framework for Early Recognition of High-Stress Students to Support Academic Intervention
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
This study creates a machine learning framework for early identification of studentstress and analyzes various categorization techniques. Method: A dataset of PSS-14 responseswas preprocessed with cleaning, reverse scoring, encoding, and feature scaling. Five machinelearning algorithms (KNN, Decision Tree, Random Forest, Naïve Bayes, and SVM) were trainedin a 70:30 split and evaluated for accuracy, precision, recall, F1-score, confusion matrix, and 10-fold cross-validation. Findings: SVM performed the best, with 91.33% cross-validationaccuracy and 90.8% test accuracy, correctly classifying students into three stress levels: high,moderate, and low. Novelty: The framework promotes early identification of stress, enablingtimely coaching, counseling, and academic support to improve student well-being andperformance.
Fields of Study & Subjects
Online Learning and Analytics
Artificial Intelligence in Healthcare
Student Stress and Coping
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 1 January 2026
- Language
- EN