AI Flags Failing Online Students in Weeks — and Shows Its Work
Researchers have built an explainable, fairness-audited early warning system that predicts online student dropout using only the first weeks of ...
Researchers have built an explainable, fairness-audited early warning system that predicts online student dropout using only the first weeks of ...
A new conceptual framework argues that AI in university assessment succeeds or fails not on technical capability alone but on ...
Researchers at Damietta University used automated machine learning to predict medical student performance, finding that ensemble methods like Bagging and ...
A new study in Mobile Networks and Applications combines Shannon entropy, response times and facial-expression analysis to show that electronic ...
Researchers in Gaza show that internet-induced exam failures leave detectable signatures in learning management system logs, allowing institutions to separate ...
Researchers have built a leakage-controlled two-level clustering framework that profiles the cognitive strengths of nearly 37,000 university students and stratifies ...
A two-week pilot of SmartPD, an AI-assisted micro-learning model aligned with the DigCompEdu framework, produced significant gains in teachers' digital ...
A new framework called EKT-XAI processes 95 million student interactions in minutes using a lightweight transformer that matches deep knowledge ...
A continuing global research-mapping project identifies and interprets the critical directions shaping digital education’s technological, policy and ethical future.
A study finds that adding hierarchical relationships among knowledge components can improve knowledge-tracing predictions and clarify students’ learning difficulties.
© 2026 Scienmag - Science Magazine
© 2026 Scienmag - Science Magazine