DIGITAL MEASUREMENT OF EMPLOYEE STRESS AND FATIGUE IN ARTIFICIAL INTELLIGENCE-DRIVEN WORKFORCE MANAGEMENT ENVIRONMENTS: AN EMPIRICAL STUDY USING AICOACH

Abstract

Effective fatigue management in the workplace is associated with employee well-being, safety, and productivity. Fatigue, often resulting from inadequate rest and high workloads, can lead to decreased cognitive function, diminished job performance, and increased risk of accidents, thus affecting both individual health and organizational efficiency. For this, we introduced an innovative approach to understanding and addressing workplace fatigue. By analyzing the interrelationships between employees' self-reported fatigue levels, their perceptions of managing fatigue, and their engagement with an AI-based coaching tool (AiCoach), we sought to uncover patterns that could inform more effective fatigue management strategies. Using advanced sentiment analysis adapted for the context of fatigue and Granger-causality tests, we examined these dynamics over time. Our findings highlight the importance of immediate perceptions of fatigue in predicting engagement with management interventions, underscoring the need for real-time monitoring and adaptive strategies in managing workplace fatigue.