Journal of the Korean Society of Safety (한국안전학회지)

The Korean Society of Safety (한국안전학회)
권호 표지
DOI QR코드

DOI QR Code

Text-mining based Cause Analysis of Accidents at Workplaces in Korea

텍스트 마이닝 기법을 활용한 우리나라 산업재해의 원인분석

  • Choi, Gi Heung (Department of Mechanical Systems Engineering, Hansung University)
  • 최기흥 (한성대학교 기계시스템공학과)
  • Received : 2022.03.23
  • Accepted : 2022.05.24
  • Published : 2022.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

The analysis of the causes of accidents in workplaces where machines and tools are used is essential to improve the effectiveness and efficiency of safety prevention policies in places of employment in Korea. The causes of workplace accidents are not fully understood mainly due to difficulties in analyzing available descriptive information. This study focuses on the automated accident cause analysis in workplaces based on the accident abstracts found in industrial accident reports written in an unstructured descriptive format. The method proposed in this paper is based on text data mining and uses the keyword search function of Excel software to automate the analysis. The analysis results indicate that the primary reason for the frequency of accidents is related to technical aspects at a stage in which dangerous situations occur in the workplace. Accidents due to managerial causes are typically observed when danger exists in the workplace; however, managerial actions play a more important role in reducing accident severity. A small company tends to use unsafe machines and devices, leading to further accidents due to technical causes, whereas managerial causes are more conspicuous as the company grows. To preclude the occurrence of accidents due to inadequate knowledge, the implementation of safety management and the provision of safety education to elderly workers at the early stage of their employment are particularly important for small companies with less than 100 workers.

Keywords

Acknowledgement

This study was supported by Hansung University.

References

  1. Yearly Industrial Accident Analysis Report, KOSHA, 2012-2017.
  2. Health and Safety Executive. Health and Safety in Manufacturing Sector in Great Britain 2014/2015; 2016.
  3. Health and Safety Executive. Health and safety in Construction Sector in Great Britain 2014/2015; 2016.
  4. G. H. Choi, "Improvement of Reliability in Cause Analysis of Industrial Accidents", J. Korean Soc. Saf., Vol. 29, No. 6, pp. 1-8, 2014. https://doi.org/10.14346/JKOSOS.2014.29.6.001
  5. G. H. Choi, "Cause Analysis of Accidents Associated with Industrial Machines and Devices", J. Korean Soc. Saf., Vol. 33, No. 1, pp. 16-21, 2018. https://doi.org/10.14346/JKOSOS.2018.33.1.16
  6. G. H. Choi, Cause Analysis of Accidents Associated with Dangerous Machines and Devices Subject to Safety Certification, J. Korean Soc. Saf., Vol. 35, No. 4, pp. 1-8, 2020. https://doi.org/10.14346/JKOSOS.2020.35.4.1
  7. G. H. Choi, "Adjustment of Industrial Machines and Devices Subject to Safety Certification, Self-declaration of Conformity and Safety inspection", Research Report, Occupational Safety and Health Certification Institute, 2018.
  8. Wikipedia, https://en.wikipedia.org/wiki/Text_mining#cite_note-2
  9. A Hotho, A Nurnberger, and G Paass, "A brief Survey of Text Mining", In Ldv Forum, Vol. 20, No. 1, pp. 19-62, 2005.