Journal of Korean Society of Disaster and Security (한국방재안전학회논문집)

Korean Society of Disaster & Security (한국방재안전학회)
권호 표지
DOI QR코드

DOI QR Code

Research Suggestion for Disaster Prediction using Safety Report of Korea Government

안전신문고를 이용한 재난 예측 방법론 제안

  • Lee, Jun (Transport Safety & Disaster Prevension Research Center, Korea Transport Institute (KOTI)) ;
  • Shin, Jindong (Safety Research Division, National Disaster Management Research Institute (NDMI)) ;
  • Cho, Sangmyeong (Life Safety Policy Bureau, Ministry of the Interior and Safety (MOIS)) ;
  • Lee, Sanghwa (Industrial-Academic Cooperation Foundation, Mokwon University)
  • 이준 (한국교통연구원 안전방재연구센터) ;
  • 신진동 (국립재난안전연구원 안전연구실) ;
  • 조상명 (행정안전부 안전정책실) ;
  • 이상화 (목원대학교 산학협력단)
  • Received : 2019.11.14
  • Accepted : 2019.12.16
  • Published : 2019.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

Anjunshinmungo (The safety e-report) has been in operation since 2014, and there are about 1 million cumulative reports by June 2019. This study analyzes the contents of more than 1 million safety newspapers reported at the present time of information age to determine how powerful and meaningful the people's voice and interest are. In particular, we are interested in forecasting ability. We wanted to check whether the report of the safety newspaper was related to possible disasters. To this end, the researchers received data reported in the safety newspaper as text and analyzed it by natural language analysis methodology. Based on this, the newspaper articles during the analysis of the safety newspaper were analyzed, and the correlation between the contents of the newspaper and the newspaper was analyzed. As a result, accidents occurred within a few months as the number of reports related to response and confirmation increased, and analyzing the contents of safety reports previously reported on social instability can be used to predict future disasters.

안전신문고는 2014년부터 운영되고 있으며, 2019년 7월까지 약 1백만 건의 누적신고건수가 존재한다. 본 연구에서는 정보화시대가 되고 있는 현 시점에서 약 116만 건이 넘은 안전신문고의 신고내용을 분석하여 국민의 소리와 관심이 과연 얼마나 힘이 있고 의미가 있는지 확인하고자 한다. 특히, 예측능력에 관심을 두고 있는데, 과연 안전신문고의 신고내용이 향후 일어날 수 있는 재난과 연관성이 있는지 확인하고자 하였다. 이를 위해 연구진은 안전신문고에 신고된 자료를 텍스트로 받아 자연어 분석 방법(Natural Language Processing)론에 의해 분석하였다. 이를 토대로 안전신문고 분석 기간 동안의 신문기사를 분석하여 안전신문고와 신문 기사 내용 간의 상관관계를 분석하였다. 그 결과 응답 및 확인 관련 보고서의 수가 증가함에 따라 몇 달 내 사고가 발생하였으며, 사회의 불안에 대해 사전에 보고된 안전문고의 내용을 분석하면 미래 재난 예측에 활용될 수 있을 것이라 판단된다.

Keywords

References

  1. Bae, Y. M. (1998). A Study on the Preventive Education for Adolescents' Problems in Home Economics Education - Adolescents' Culture Analyzed with Newspaper Articles Concerning Adolescents. Korean Home Economics Education Association. 10(2): 131-144.
  2. Baek, Y. (2017). Text Mining Using R. Press Hanwool. pp. 171-178.
  3. Blei, D. M., Ng, A. Y., and Jordan, M. I. (2003). Latent Dirichlet Allocation. Journal of Machine Learning Research. 3: 993-1022.
  4. Cho, J. Y., Kim, H. S., and Cho, M. J. (2018). A Study on the Change of Issues with Adolescent Problem by Using Text Mining - The Internet News Articles for the Years 2008 to 2018. Journal of Educational Innovation Research. 28(4): 461-487. https://doi.org/10.21024/pnuedi.28.4.201812.461
  5. Chung, B. M., Kim, T. W., Lee, J., and Chung, J. S. (2015). Twitter Topic Extraction and Topic Category Decision using LDA Model. Korea Institute of Information Sciencetists An Engineers, Proceeding. pp. 787-788
  6. Chung, D. Y., LEE, J. S., and Park, S. S. (2016). Technology Trend Analysis using Wordcloud. Confernce Proceeding of Korean Institute of Intellignet Systems. 26(1): 17-18.
  7. Dancey, C. and Reidy, J. (2011). Statistics without Maths for Psychology. Prentice Hall. 5th edition. p. 175.
  8. Hwang, H. S. (1998). Stemming Methodology for Natural Language Processing. Phrasebook. 37: 439-440.
  9. Kang, H. B., Kang, J. H., Rye, Y. N., Son, J. Y., Yoon, B. Y., and Lee, J. S. (2017). A Study on the Usability of Opinion Mining in Post-Occupancy Evaluation. The 17th Proceedings of the Architectural Institute of Korea Conference. 37(2): 1144-1146.
  10. Kim, Y. H. (2003). Social Netwok Analysis. Barkyoung Press.
  11. Lim, D. S. (2001). Error Types of Word-class Analysis in Korean-English Bilingual Children. Master Thesis. Yeonsei University.
  12. Park, S. J. (2015). A Topic Analysis of SW Education Textdata Using R. Korean Association of Information Education. 19(4): 517-524. https://doi.org/10.14352/jkaie.2015.19.4.517
  13. Thanaki, J. (2019). Python Natural Language Processing (Advanced Machine Learning and Deep Learning Techniques for Natural Language Processing). Packt Press.
  14. Yoon, T. I. (2019). Text Analysis Using Python. Nulbom Press.