Safeguarding Privacy: Privacy-Preserving Detection of Mind Wandering and Disengagement Using Federated Learning in Online Education

2026-02-10

AI Summary

This study addresses the challenge of detecting cognitive disengagement—such as inattention, mind wandering, and fatigue—in online learning environments, where limited instructor supervision exacerbates the issue and existing video-based detection methods raise significant privacy concerns. To this end, the authors propose a privacy-preserving, cross-device federated learning framework that enables real-time detection of cognitive disengagement without collecting raw video data. The approach integrates multimodal cues including facial expressions, gaze direction, and, for the first time, eyeglasses-wearing status to enhance model robustness. Validated through collaborative training across five real-world datasets, the method demonstrates substantial improvements in generalization performance, offering a viable pathway toward intelligent educational technologies that simultaneously ensure user privacy and provide timely learning support.

Technology Category

• Machine Learning: Privacy
• Computer Vision: Bias, Fairness & Privacy
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling

Abstract

Since the COVID-19 pandemic, online courses have expanded access to education, yet the absence of direct instructor support challenges learners'ability to self-regulate attention and engagement. Mind wandering and disengagement can be detrimental to learning outcomes, making their automated detection via video-based indicators a promising approach for real-time learner support. However, machine learning-based approaches often require sharing sensitive data, raising privacy concerns. Federated learning offers a privacy-preserving alternative by enabling decentralized model training while also distributing computational load. We propose a framework exploiting cross-device federated learning to address different manifestations of behavioral and cognitive disengagement during remote learning, specifically behavioral disengagement, mind wandering, and boredom. We fit video-based cognitive disengagement detection models using facial expressions and gaze features. By adopting federated learning, we safeguard users'data privacy through privacy-by-design and introduce a novel solution with the potential for real-time learner support. We further address challenges posed by eyeglasses by incorporating related features, enhancing overall model performance. To validate the performance of our approach, we conduct extensive experiments on five datasets and benchmark multiple federated learning algorithms. Our results show great promise for privacy-preserving educational technologies promoting learner engagement.

Problem

• mind wandering
• disengagement
• privacy-preserving
• online education
• federated learning

Innovation

• federated learning
• privacy-preserving
• mind wandering detection
• cognitive disengagement
• online education