The Analysis of Natural Disasters in China from 1998 to 2016 based on Text Mining

DOI

10.2991/rac-16.2016.54How to use a DOI?

Keywords

Natural disasters, text mining, spatial association, disaster distribution

Abstract

This paper takes the 248 disaster events happened in China from 1998 to 2016 as samples, uses text mining, descriptive statistics, association rules and other methods to implement event extraction for disaster events in history, and then analyzes characteristics of the disasters including type, location and time. The results show that Flood, earthquake, landslide, typhoon and rainstorm are found to be the most frequent natural disasters in China, according to the analysis of disasters time .most of disasters were occurred during May to August, specially flood and heavy rain. In the end, the paper analyzes the spatial distribution of disasters .The results show a significant difference of the geographical locations among different types of disasters. And Yunnan is the region where the most times of disasters happened. In addition, the spatial association of disaster events is also analyzed. The result of this study will offer insight into the identification of disaster risks and carrying out the disaster prevention and mitigation.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Xiao Liu
AU  - Haixiang Guo
AU  - Yijing Li
AU  - Chunmiao Yang
PY  - 2016/11
DA  - 2016/11
TI  - The Analysis of Natural Disasters in China from 1998 to 2016 based on Text Mining
BT  - Proceedings of the 7th Annual Meeting of Risk Analysis Council of China Association for Disaster Prevention
PB  - Atlantis Press
SP  - 335
EP  - 342
SN  - 1951-6851
UR  - https://doi.org/10.2991/rac-16.2016.54
DO  - 10.2991/rac-16.2016.54
ID  - Liu2016/11
ER  -