From unstructured accident reports to a hybrid decision support system for occupational risk management: The consensus converging approach.

INTRODUCTION: Workplace accidents in the petroleum industry can cause catastrophic damage to people, property, and the environment. Earlier studies in this domain indicate that the majority of the accident report information is available in unstructured text format. Conventional techniques for the analysis of accident data are time-consuming and heavily dependent on experts' subject knowledge, experience, and judgment. There is a need to develop a machine learning-based decision support system to analyze the vast amounts of unstructured text data that are frequently overlooked due to a lack of appropriate methodology. METHOD: To address this gap in the literature, we propose a hybrid methodology that uses improved text-mining techniques combined with an un-bias group decision-making framework to combine the output of objective weights (based on text mining) and subjective weights (based on expert opinion) of risk factors to prioritize them. Based on the contextual word embedding models and term frequencies, we extracted five important clusters of risk factors comprising more than 32 risk sub-factors. A heterogeneous group of experts and employees in the petroleum industry were contacted to obtain their opinions on the extracted risk factors, and the best-worst method was used to convert their opinions to weights. CONCLUSIONS AND PRACTICAL APPLICATIONS: The applicability of our proposed framework was tested on the data compiled from the accident data released by the petroleum industries in India. Our framework can be extended to accident data from any industry, to reduce analysis time and improve the accuracy in classifying and prioritizing risk factors.

Injury count model for quantification of risk of occupational injury.

Reduction of risk of occupational injuries is one of the most challenging problems faced by industry. Assessing and comparing risks involved in different jobs is one of the important steps towards reducing injury risk. In this study, a comprehensive scheme is given for assessing and comparing injury risks with the development of injury count model, injury risk model and derived statistics. The hazards present in a work system and the nature of the job carried out by workers are perceived as important drivers of injury potential of a work system. A loglinear model is used to quantify injury counts and the event-tree approach with joint, marginal and conditional probabilities is used to quantify injury risk. A case study was carried out in an underground coal mine. Finally a number of indices are proposed for the case study mine to capture risk of injury in different jobs. The findings of this study will help in designing injury intervention strategies for the mine studied. The job-wise risk profiles will be used to prioritise the jobs for redesign. The absolute indices can be applied for benchmarking job-wise risks and the relative indices can be used for comparing job-wise risks across work systems.