University Job Stress Management System: An Explainable Artificial Intelligence Approach for Nigerian Universities

Abstract

University staff in Nigeria experience escalating job stress driven by chronic underfunding, administrative burdens, infrastructural deficits, and evolving pedagogical demands, adversely affecting well-being and institutional performance. Traditional stress management interventions often lack scalability, personalization, and cultural relevance in this context. This study addresses the gap by developing and validating a novel Job Stress Management System (JSMS) tailored for Nigerian university workers, leveraging Explainable Artificial Intelligence (XAI). Employing a multi-phase design science research methodology, the study integrated literature review, mixed-methods fieldwork with 427 staff across 15 universities, and iterative system development. The major stressors identified included excessive workload (68.2%), poor remuneration (62.7%), inadequate infrastructure (58.9%), bureaucratic delays (55.2%), and perceived lack of support (49.1%). The JSMS features a lightweight web application powered by an XAI engine using SHAP and LIME techniques on top of ensemble models (XGBoost, Random Forest), trained on validated stress assessment data. It delivers real-time stress prediction, personalized coping recommendations, resource linkage, and transparent, interpretable explanations for predictions. A 12- week pilot with 120 participants demonstrated significant reductions in self-reported stress (mean reduction 32.7%, p<0.001), high system trust (87.3% attributed trust to explainability), and strong perceived usefulness (mean score 4.3/5.0). The studycontributes a contextually grounded, ethically designed, and practically implementable JSMS framework, advancing XAI applications for human centric HRM solutions in resource-constrained, culturally specific settings. It offers actionable insights for Nigerian university administrators, policymakers, and HR practitioners, with transferable relevance to similar global contexts facing systemic workplace stress challenges.