Scholarlink

<p>Roof accidents were identified as a major hazard to coal mine safety, and the analysis of 326 relevant literature items using CiteSpace reflected a growing research trend in this field. Traditional hazard identification methods were heavily dependent on expert judgment, predefined models, and manual processing, which resulted in strong subjectivity, low efficiency, and limited adaptability in handling unstructured accident texts. To address this challenge, an integrated framework combining Chinese word segmentation with the TF-IDF algorithm was proposed to automatically extract and quantify roof hazard factors. This method was applied to 115 unstructured roof accident reports to identify and quantify hazard factors, with final results indicating a 26% and 35% reduction in redundant information for direct and indirect causes, respectively. Additionally, key hazard phrases were extracted and objectively weighted by this approach. Key direct causes include mine worker, work against regulations, and untimely support measures, among others; indirect causes involve inadequate safety education and training, lack of operational regulation, and failure to implement hidden danger investigation and management.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Research on the roof hazard factors quantification based on Chinese word segmentation and TF-IDF algorithm

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月20日

查看全文
  • Dongxu Jia,
  • Guowei Zhang,
  • Jun Han,
  • Ting Ren,
  • Chengwu Wang,
  • Weinan Liu

摘要

Roof accidents were identified as a major hazard to coal mine safety, and the analysis of 326 relevant literature items using CiteSpace reflected a growing research trend in this field. Traditional hazard identification methods were heavily dependent on expert judgment, predefined models, and manual processing, which resulted in strong subjectivity, low efficiency, and limited adaptability in handling unstructured accident texts. To address this challenge, an integrated framework combining Chinese word segmentation with the TF-IDF algorithm was proposed to automatically extract and quantify roof hazard factors. This method was applied to 115 unstructured roof accident reports to identify and quantify hazard factors, with final results indicating a 26% and 35% reduction in redundant information for direct and indirect causes, respectively. Additionally, key hazard phrases were extracted and objectively weighted by this approach. Key direct causes include mine worker, work against regulations, and untimely support measures, among others; indirect causes involve inadequate safety education and training, lack of operational regulation, and failure to implement hidden danger investigation and management.