A fuzzy Bayesian network DEMATEL model for predicting safety behavior

Area of Science:

• Occupational Health and Safety
• Behavioral Science
• Data Modeling

Background:

• Workplace safety behavior is crucial for overall safety performance.
• Effective management and improvement of safety behavior are essential in high-risk industries.
• Bayesian networks (BN) offer a framework for modeling complex causal relationships.

Purpose of the Study:

• To develop a Bayesian network (BN) model for managing and improving workplace safety behavior.
• To identify key factors influencing safety behavior in the chemical industry.
• To determine optimal intervention strategies for enhancing safety behavior.

Main Methods:

• Data collected via questionnaire from chemical industry workers in Iran (13 variables).
• Bayesian network structure developed using fuzzy decision-making trial, evaluation laboratory (DEMATEL) method, and expert opinions.
• Belief updating used to identify significant predictors of safety behavior.

Main Results:

• Locus of control, organization safety priority, and safety knowledge identified as the strongest predictors of safety behavior.
• Improving organization safety priority and safety knowledge emerged as the most effective intervention strategy.
• The BN model effectively illustrates causal links between variables influencing safety behavior.

Conclusions:

• Bayesian networks are powerful tools for modeling causal relationships in safety management.
• Prioritizing organizational safety and enhancing safety knowledge significantly improve safety behavior.
• The study provides a data-driven approach to optimize safety interventions in industrial settings.