Developing a Socio-Technical Governance Framework for AI-Driven Mental Health Monitoring in Higher Education and Digital Behavioral Care Networks

• Abey city

  Lautech

  Author

The rising prevalence of student mental health crises in higher education has outpaced traditional counseling resources, prompting the exploration of AI-driven monitoring systems that analyze digital behavioral data (e.g., LMS activity, communication patterns). However, existing approaches lack validated governance frameworks that balance predictive accuracy with ethical safeguards, creating a critical research gap. This study addresses this gap by developing and testing a novel Socio-Technical Governance Framework (STGF) for algorithmic vigilance. Using a design-based research methodology, we integrated retrospective digital exhaust data (n=2,450 students) with prospective agent-based simulations across three university settings. Key findings demonstrate that a hybrid random forest-LSTM model achieves 89.4% accuracy (F1=0.87, AUC=0.92) in predicting moderate-to-severe distress episodes 14–21 days in advance, significantly outperforming baseline methods (p<0.001). The STGF reduced false positive alerts by 41.2% compared to unconstrained monitoring. The main conclusion is that effective ethical algorithmic vigilance is technically achievable but requires mandatory human-in-the-loop review, dynamic consent protocols, and algorithmic transparency thresholds. Practical implications include a replicable audit framework for university counseling centers and digital behavioral care networks.

• PDF

Copyright (c) 2026 Abey city (Author)

This work is licensed under a Creative Commons Attribution 4.0 International License.