KSCE Journal of Civil and Environmental Engineering Research (대한토목학회논문집)

Korean Society of Civil Engeneers (대한토목학회)
권호 표지
DOI QR코드

DOI QR Code

Analysis of Seasonal Importance of Construction Hazards Using Text Mining

텍스트마이닝을 이용한 건설공사 위험요소의 계절별 중요도 분석

  • 박기창 (연세대학교 기후변화 적응형 사회기반시설 연구센터) ;
  • 김형관 (연세대학교 건설환경공학과)
  • Received : 2020.06.29
  • Accepted : 2020.10.16
  • Published : 2021.06.01
Download PDF
⟨ Previous Next ⟩

Abstract

Construction accidents occur due to a number of reasons-worker carelessness, non-adoption of safety equipment, and failure to comply with safety rules are some examples. Because much construction work is done outdoors, weather conditions can also be a factor in accidents. Past construction accident data are useful for accident prevention, but since construction accident data are often in a text format consisting of natural language, extracting construction hazards from construction accident data can take a lot of time and that entails extra cost. Therefore, in this study, we extracted construction hazards from 2,026 domestic construction accident reports using text mining and performed a seasonal analysis of construction hazards through frequency analysis and centrality analysis. Of the 254 construction hazards defined by Korea's Ministry of Land, Infrastructure, and Transport, we extracted 51 risk factors from the construction accident data. The results showed that a significant hazard was "Formwork" in spring and autumn, "Scaffold" in summer, and "Crane" in winter. The proposed method would enable construction safety managers to prepare better safety measures against outdoor construction accidents according to weather, season, and climate.

건설사고는 근로자의 부주의, 안전장비 미착용, 안전규칙 미준수 등 다양한 요인이 복합적으로 작용해 발생할 수 있다. 건설사고를 유발하는 여러 요인 중 야외작업이 많은 건설업의 특성상 기상 조건은 건설사고 발생 요인 중 하나가 될 수 있다. 과거 발생한 건설사고 데이터는 사고예방을 위한 좋은 자료로 활용될 수 있지만, 건설업 재해사례 데이터는 자연어로 기술된 텍스트형태로 제공되기 때문에 건설업 재해사례 데이터에서 건설공사 위험요소(Hazard)를 추출하는 것은 많은 시간과 비용이 발생한다. 따라서, 본 연구에서는 텍스트마이닝을 이용해 국내에서 발생한 2,026건의 건설업 재해사례 텍스트데이터에서 건설공사 위험요소를 추출하고 빈도 분석(Frequency analysis)과 중심성 분석(Centrality analysis)을 통해 건설공사 위험요소의 계절별 중요도분석을 수행했다. 국토교통부에서 정의한 254개 건설공사 위험요소 중 51개 위험요소를 건설사고 텍스트데이터에서 추출했으며, 분석결과 봄, 가을은 거푸집, 여름은 비계, 겨울은 크레인이 계절별 가장 중요한 위험요소로 나타났다. 제안방법은 날씨, 계절, 기후 관련 건설사고 안전대책 마련에 활용될 수 있다.

Keywords

Acknowledgement

이 논문은 2018년도 정부(교육부)의 재원으로 한국연구재단의 지원을 받아 수행된 기초연구사업임(No. 2018R1A6A1A08025348).

References

  1. Bastian, M., Heymann, S. and Jacomy, M. (2009). "Gephi: An open source software for exploring and manipulating networks." 3rd International AAAI Conference on Weblogs and Social Media, San Jose, California, pp. 361-362.
  2. BeautifulSoup (2020). Beautiful soup documentation, Available at: https://www.crummy.com/software/BeautifulSoup/bs4/doc/ (Accessed: June 25, 2020).
  3. Blondel, V. D., Guillaume, J. L., Lambiotte, R. and Lefebvre, E. (2008). "Fast unfolding of communities in large networks." Journal of Statistical Mechanics: Theory and Experiment, DOI: 10.1088/1742-5468/2008/10/P10008.
  4. Das, K., Samanta, S. and Pal, M. (2018). "Stu dy on centrality measures in social network: A survey." Social Network Analysis and Mining, Vol. 8, No. 13, DOI: 10.10007/s13278-018-0493-2.
  5. Goh, Y. M. and Ubeynarayana, C. U. (2017). "Construction accident narrative classification: An evaluation of text mining techniques." Accident Analysis & Prevention, Vol. 108, pp. 122-130. https://doi.org/10.1016/j.aap.2017.08.026
  6. Jallan, Y., Elizabeth B., Baabak A. and Caroline, M. C. (2019). "Application of natural language processing and text mining to identify patterns in construction-defect litigation cases." Journal of Legal Affairs and Dispute Resolution in Engineering and Construction, Vol. 11, No. 4, DOI:10.1061/%28ASCE%29LA.1943-4170.0000308.
  7. Jeong, S. S., Bae, D. H., Kim, H. K., Kim, J. H., Lee, J. H., Kim, S. E., Park, S. K., Kim, J. H., Yun, T. S., Mun, S. H., Park, J. H. and Kang, H. J. (2017). Climate change-induced infrastructure design manual, Korean Society of Civil Engineers Press, KSCE (in Korean).
  8. Kim, J. S. and Kim, B. S. (2019). "Characteristics analysis of seasonal construction site fall accident using text mining." Korean Journal of Construction Engineering and Management, Vol. 20, No. 3, pp. 113-121 (in Korean). https://doi.org/10.6106/KJCEM.2019.20.3.113
  9. Kim, S., Lim, S. Y., Park, M. S. and Kim, K. T. (2016). "Text mining analysis for instigating international research trend in construction automation." Proceedings of 2016 Korean Society of Civil Engineers, KSCE, pp. 51-52 (in Korean).
  10. Kim, T. H. and Chi, S. H. (2019). "Accident case retrieval and analysis: Using natural language processing in the construction industry." Journal of Construction Engineering and Management, Vol. 145, No. 3, DOI: 10.1061/%28ASCE%29CO.1943-7862.0001625.
  11. Kim, Y. H., Jeong, J. H., Kang, D. B., Park, K. M. and Kim, S. M. (2015). "Trend analysis of research topics in journal of lifelong learning society: Using network text analysis." Journal of Lifelong Learning Society, Vol. 11, No. 1, pp. 291-315 (in Korean). https://doi.org/10.26857/JLLS.2015.02.11.1.291
  12. Lee, G. T., Moon, S. H., Oh, H. C., Shin, Y. H. and Chi, S. H. (2018). "Non-compliance specification checking based on textmining construction standard analysis." Proceedings of 2018 Korean Society of Civil Engineers, KSCE, pp. 269-270 (in Korean).
  13. Marzouk, M. and Enaba, M. (2019). "Text analytics to analyze and monitor construction project contract and correspondence." Automation in Construction, Vol. 98, pp. 265-274. https://doi.org/10.1016/j.autcon.2018.11.018
  14. McInnes, J. A., MacFarlane, E. M., Sim, M. R. and Smith, P. (2018). "The impact of sustained hot weather on reisk of acute work-related injury in Melbourne, Australia." International Journal of Biometeorology, Vol. 62, pp. 153-163. https://doi.org/10.1007/s00484-017-1435-9
  15. Ministry of Land, Infrastructure and Transport (MOLIT) (2014). Development of risk factor for construction project, MOLIT Research Report (in Korean).
  16. National Institute of Meteorological Sciences (NIMS) (2018). Climate change in the Korean peninsula for 100 years, NIMS Research Report (in Korean).
  17. Park, E. J. and Cho, S. Z. (2014). "KoNLPy: Korean natural language processing in Python." Proceedings of the 26th Annual Conference on Human & Cognitive Language Technology (in Korean).
  18. Park, M. H. (2016). "The analysis of knowledge structure using Co-word method in quality management field." Journal of the Korean Society for Quality Management, Vol. 44, No. 2, pp. 389-408 (in Korean). https://doi.org/10.7469/JKSQM.2016.44.2.389
  19. Scikit-learn (2020). Scikit-learn machine learning in python, Available at: https://scikit-learn.org (Accessed: June 25, 2020).
  20. Song, J., Hu, R., Sun, B., Gu, Y., Xiong, W. and Zhu, J. (2019). "Research on news keyword extraction based on TF-IDF and Chinese features." Proceedings of 2019 2nd International Conference on Financial Management, Education and Social Science, FMESS, Huhhot, China, pp. 334-342.
  21. Wang, Y., Li, H. and Wu, Z. (2019). "Attitude of the Chinese public toward off-site construction: A text mining study." Journal of Cleaner Production, Vol. 238, DOI: 10.1016/j.jclepro.2019.117926.
  22. Yoon, S. Y. and Yoon, D. K. (2018). "Analysis of direct and indirect impacts of seismic risk using text mining." Proceedings of 2018 Korean Society of Civil Engineers, KSCE, pp. 8-10 (in Korean).
  23. Yun, J. H., Ryu, E. J. and Lee, S. Y. (2018). "Text network analysis related to disclosure of cancer diagnosis among Korea and other countries." Asian Oncology Nursing, Vol. 18, No. 3, pp. 154-162 (in Korean). https://doi.org/10.5388/aon.2018.18.3.154
  24. Zhang, F., Fleyeh, H., Wang, X. and Lu, M. (2019). "Construction site accident analysis using text mining and natural language processing techniques." Automation in Construction, Vol. 99, pp. 238-248. https://doi.org/10.1016/j.autcon.2018.12.016
  25. Zhong, B., Pan, X., Love, P. E., Ding, L. and Fang, W. (2020). "Deep learning and network analysis: Classifying and visualizing accident narratives in construction." Automation in Construction, Vol. 113, 103089. https://doi.org/10.1016/j.autcon.2020.103089