A New Text-Mining–Bayesian Network Approach for Identifying Chemical Safety Risk Factors

Abstract

The frequent occurrence of accidents in the chemical industry has caused serious economic loss and negative social impact. The chemical accident investigation report is of great value for analyzing the risk factors involved. However, traditional manual analysis is time-consuming and labor-intensive, while existing keyword extraction methods still need to be improved. This study aims to propose an improved text-mining method to analyze a large number of chemical accident reports. A workflow was designed for building and updating lexicons of word segmentation. An improved keyword extraction algorithm was proposed to extract the top 100 keywords from 330 incident reports. A total of 51 safety risk factors was obtained by standardizing these keywords. In all, 294 strong association rules were obtained by Apriori. Based on these rules, a Bayesian network was built to analyze safety risk factors. The mean accuracy and mean recall of the BM25 model in the comparison experiments were 10.5% and 14.38% higher than those of TF-IDF, respectively. The results of association-rule mining and Bayesian network analysis can clearly demonstrate the interrelationship between the safety risk factors. The methodology of this study can quickly and efficiently extract key information from incident reports which can provide managers with new insights and suggestions.

An Operator Training Simulator to Enable Responses to Chemical Accidents through Mutual Cooperation between the Participants

“…The chemical industry involves diverse and complex processes and handles flammable, explosive, and hazardous chemicals; therefore, chemical accidents are frequent, and losses are large within this industry [1]. The Flixborough (1974), Seveso (1976), Three Mile Island (1979), Bhopal (1984), and Chernobyl (1986) disasters are representative accidents in the petrochemical industry, all of which were caused by human error [2].…”