Establishment of a Key Hidden Danger Factor System for Electric Power Personal Casualty Accidents Based on Text Mining

Based on actual safety management difficulties and needs, this paper aims to screen extract the key accident potential factors of personal injuries deaths within electric power industry provide a reference for companies’ prevention effort. First, document sorts out analyzes all causes influencing elements that may lead occurrence deaths, based which rough are initially identified combined with definition potentials. Second, mines relevant report texts using text-mining technologies such as term count, word cloud, frequency–inverse frequency (TF-IDF), thus system industry, including three (human, material, management), is finally constructed. Workers’ habitual violation behavior, in particular, has larger risk than other components, implying additional steps should be made eradicate type critical time.