Text-Data Reduction Method to Grasp the Sequence of a Disaster Situation: Case Study of Web News Analysis of the 2015 Typhoons 17 and 18-Reference-Cited by-同舟云学术

Text-Data Reduction Method to Grasp the Sequence of a Disaster Situation: Case Study of Web News Analysis of the 2015 Typhoons 17 and 18

Published:2017-03-16 Issue:2 Volume:12 Page:329-334
ISSN:1883-8030
Container-title:Journal of Disaster Research
language:en
Short-container-title:J. Disaster Res.

Author:

Sato Shosuke, ,Okamoto Toru,Koshimura Shunichi,

Abstract

This study aims to compress web news, delivered as a big-data source after disasters. In this paper, article clustering, which is a combination of conventional means and an algorithm that selects the representative articles of each cluster, is designed and adopted. Experiments are conducted by evaluators. The proposed algorithm is in accord with the evaluators for 50s% of the clustering and for about 30s% to 40s% of the representative-article selection.

Publisher

Fuji Technology Press Ltd.

Subject

Engineering (miscellaneous),Safety, Risk, Reliability and Quality

Reference12 articles.

1. H. Hayashi, “Goal to ‘Development of crisis management system suitable for Japan society’,” Research workshop abstract, MEXT Science and Technology Promotion, pp. 9-23, 2006.

2. ITS Japan：Actual Traffic Data, http://www.its-jp.org/saigai/ [accesssed Oct. 3, 2016]

3. TR Analysis on Disastster and Crisis Informatin, http://www.trendreader.jp/tr_analysis/tr_portal.html [accessed Apr. 1, 2015]

4. S. Sato, H. Hayashi, N. Maki, and M. Inoguchi, “The Development of an Algorithm Using the TFIDF / TF Index to Extract Automatically the Set of Keywords of Corpus about Fields Related to Emergency Management – A Case Study Utilizing Web News Articles for the 2004 Niigata-Ken-Chuetsu Earthquake Disaster –,” J. of Social Saftey Science, No.8, pp. 367-376, 2006.

5. S. Sato, H. Hayashi, K. Inoue, and T. Nihino, “Visualizing Chronological Behavior of Disaster Social Aspect Based on Web News Articles on Disasters and Crises – Support of Creating Common Operational Picture for National/Local Government Officers and Researchers Related to Disaster Management through the Web Publication of Keyword Extraction Results using TRENDREADER (TR) –,” J. of the Visualization Society of Japan, Vol.29, No.7, pp. 17-26, 2009.