Objective: This study aims to tackle the increasing prevalence of employee burnout by introducing a novel hybrid methodology employing Bayesian networks and fuzzy logic. This approach seeks to identify and address burnout risks comprehensively.
Theoretical Framework: Drawing from burnout theories alongside Bayesian networks and fuzzy logic, this research establishes a robust foundation for understanding burnout complexities and evaluating the efficacy of the proposed hybrid approach.
Method: The methodology encompasses a model development phase utilizing OpenMarkov and FisPro to integrate Bayesian networks and fuzzy logic. Data collection involved a multifaceted approach including surveys, expert interviews, and a thorough review of literature focusing on workload, work environment, psychology, and other pertinent factors influencing burnout.
Results and Discussion: Findings indicate that burnout tends to manifest at lower levels in scenarios characterized by weak communication, high workload, and low obstacles, while it escalates in situations marked by weak communication, occasional workload spikes, and moderate obstacles, among other contributing factors. These results are analyzed within the context of the theoretical framework, emphasizing their implications for individual well-being and organizational success.
Research Implications: This study provides actionable insights for companies, particularly human resources managers, to bolster employee psychological support systems and advance organizational objectives. Proactively addressing burnout risks can enhance both employee well-being and overall organizational performance.
Originality/Value: By proposing a hybrid methodology that merges Bayesian networks and fuzzy logic to comprehensively tackle burnout risks, this research contributes to the existing literature. The innovative methodology and practical implications underscore the significance and applicability of this study for organizations striving to mitigate burnout within their workforce.