JDR Vol.12 No.1 pp. 67-78
doi: 10.20965/jdr.2017.p0067

Survey Report:

Disaster Information System Using Natural Language Processing

Naoko Kosaka*1,†, Akira Koyama*1, Tomohiro Kokogawa*1, Yuji Maeda*1, Hiroko Koumoto*2, Shingo Suzuki*3, Kenshi Yamaguchi*4, and Kentaro Inui*4

*1NTT Secure Platform Laboratories
3-9-11, Midori-cho Musashino-shi, Tokyo 180-8585, Japan

Corresponding author

*2Tokoha University, Shizuoka, Japan

*3National Research Institute for Earth Science and Disaster Resilience, Ibaraki, Japan

*4Tohoku University, Miyagi, Japan

August 10, 2016
January 13, 2017
February 1, 2017
natural language processing, incident response, activity log, SOP (Standard Operating Procedure)
In this paper, we analyze incident response management work using free-formed information that is important for incident response communication. We develop a standard operating procedure for the work and study a support method based on a language processing technology to prevent missing or overlapping necessary tasks and optimize management of progress and integration management of related tasks. A prototype system was developed and evaluated in a workshop held by a local government, or in an exercise. As a result, it is confirmed that the use of language processing technology can make incident response management work efficient.
Cite this article as:
N. Kosaka, A. Koyama, T. Kokogawa, Y. Maeda, H. Koumoto, S. Suzuki, K. Yamaguchi, and K. Inui, “Disaster Information System Using Natural Language Processing,” J. Disaster Res., Vol.12 No.1, pp. 67-78, 2017.
Data files:
  1. [1] Cabinet Office, Government of Japan, “Report of standardization of measures for disaster recovery,” [accessed August 1, 2016, in Japanese]
  2. [2] Ministry of Land, Infrastructure, Transport and Tourism, “DiMAPS,” [accessed August 1, 2016, in Japanese]
  3. [3] Institute of Scientific Approaches for fire and disaster, “Extinguishing fire and disaster prevention GIS,” [accessed August 1, 2016, in Japanese]
  4. [4] N. Kosaka et al., “Study of Typical/Atypical Information Utilization According to Incident Response Phases on Emergency Management Support System,” IEICE Tech. Report, ICSSSL2014-15, October, 2014 (in Japanese).
  5. [5] K. Inui et al., “Computer-Assisted Databasing of Disaster Management Information Through Natural Language Processing,” J. of Disaster Research, Vol.10, No.5, pp. 830-844, 2015.
  6. [6] F. Ichinose et al., “A Fundamental Study of Efficiency of Information Processing in Emergency Operations Center,” J. of Disaster Research, Vol.9, No.2, pp. 206-214, 2014 (in Japanese).
  7. [7] F. Ichinose et al., “Evaluation of importance of treating free-style information in disaster information system and proposal for effective utilization method,” J. of Institute of Social Safety Science, No.27, pp. 179-188, 2015 (in Japanese).
  8. [8] FEMA, “General Message (ICS 213),” [accessed August 1, 2016]
  9. [9] Homeland Security, Interoperability Continuum, “A tool for improving emergency response communication and interoperability,” [accessed August 1, 2016]
  10. [10] T. Hashimoto, T. Inui, and K. Murakami, “Constructing Extended Named Entity Annotated Corpora,” IPSJ Natural Language Processing (NL-188-17), pp. 113–120, 2008.
  11. [11] J. R. Finkel, T. Grenager, and C. Manning, “Incorporating Non-local Information into Information Extraction Systems by Gibbs Sampling, Proc. of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL 2005), pp. 363-370, 2005.
  12. [12] K. Matsuda, A. Sasaki, N. Okazaki, and K. Inui, “Annotating Geographical Entities on Microblog Text,” In Proc. of the 9th Linguistic Annotation Workshop (LAW IX 2015), pp. 85-94, June 2015.
  13. [13] C. D. Manning, P. Raghavan, and H. Schuetze, “Introduction to Information Retrieval,” Cambridge University Press, 2008.

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, Opera.

Last updated on Jul. 12, 2024