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

• Published in: Journal of safety research Vol. 89; pp. 91 - 104
• Main Authors: Gangadhari, Rajan Kumar, Rabiee, Meysam, Khanzode, Vivek, Murthy, Shankar, Kumar Tarei, Pradeep
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.06.2024
• Subjects: Accident Prevention - methods; Accidents - statistics & numerical data; Best Worst Method; Data Mining; Decision Support System; Decision Support Techniques; Electronic Data Processing; Group Decision Making; Humans; Information processing; Machine Learning; Occupational Health; Occupational Risk Prioritization; Oil and Gas Industry - statistics & numerical data; Risk Management - methods; Text mining; Workplace - standards; Workplace - statistics & numerical data; Text mining; Decision Support System; Group Decision Making; Occupational Risk Prioritization; Best Worst Method; Information processing
• ISSN: 0022-4375; 1879-1247; 1879-1247
• DOI: 10.1016/j.jsr.2024.02.006

•A decision-making framework to manage occupational risks in petroleum industries.•A novel measure of risk by integrating both objective and subjective measures.•NLP is used on unstructured accident reports to derive the objective weights.•An optimization-based group decision making framework is proposed.•5 critical clusters of risk factors along with 32 risk sub-factors are extracted. 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.