AI Driven Early Identification of Academic Stress Using Student Behavioural Patterns
This research presents an AI-driven framework for the early identification of academic stress using student behavioural patterns. The proposed approach examines indicators such as class attendance, Learning Management System (LMS) activity, assignment submission delays, study habits and sleep patterns. The study discusses data collection, preprocessing, feature engineering and supervised machine learning techniques, including Logistic Regression, Random Forest and Support Vector Machine (SVM). The objective is to identify early warning signs of academic stress and support timely intervention by educators. The research highlights the potential of behavioural analytics and artificial intelligence in promoting student well-being and improving academic outcomes. It also discusses limitations relating to dataset size, generalizability, data privacy and responsible AI.
Authors
- Dhruv Santosh Sawant
- Om Suresh Rathod
- Jayesh Dilip Koyale
- Harshvardhan Natu
Institutions
- MIT Art, Design and Technology University (IN)
Publication Details
- Journal
- Zenodo (CERN European Organization for Nuclear Research)
- Published
- 2026-11-17
- DOI
- https://doi.org/10.5281/zenodo.24321985
- Primary Topic
- Online Learning and Analytics
- Type
- preprint