Objectives. This research aims to provide information on factors that may affect the accident susceptibility of workers by using various individual characteristics of workers as variables with machine learning algorithms, and the effects of occupational health and safety (OHS) training and workers' safety awareness within this interaction. Methods. Research data were obtained through surveys administered to port workers (dockers). The data were modeled using binary logistic regression (BLR) and support vector machine (SVM) algorithms, and the results were examined comparatively. Results. Worker's profession, education level, age, safety awareness and work experience, and the number of OHS professionals are some individual characteristics and managerial factors that significantly influence whether an accident occurs or not. Employees' OHS examination scores do not have a significant impact on the likelihood of an accident for the worker. As workers believe their safety awareness is increasing, the likelihood of accidents also rises. Conclusion. Workers may have a misleading experience regarding training activities in ports and the managers' approach. They may have an unrealistic sense of self-confidence. Many accidents occurring in ports are preventable. While BLR provides a greater number of more easily interpretable outputs related to accident causality, SVM offers fewer but more reliable outputs.
Yilmaz et al. (Wed,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: