A study on urban flood damage topic model through news article text mining and latent Dirichlet allocation†
Dasom Hur1 · Jae Eun Yoo2 · Se Jin Jeung3 · Seung Kwon Jung4
1234International Center for Urban Water Hydroinformatics Research & Innovation
Correspondence to: † This work was supported by Korea Environment Industry & Technology Institute (KEITI) through R&D Program for Innovative Flood Protection Technologies against Climate Crisis Project, funded by Korea Ministry of Environment(MOE)(2022003470002).
1 Researcher, 9 Songdomirae-ro, Yeonsu-gu, Incheon 21988, International Center for Urban Water Hydroinformatics Research & Innovation. E-mail: ektha7677@gmail.com
2 Researcher, 9 Songdomirae-ro, Yeonsu-gu, Incheon 21988, International Center for Urban Water Hydroinformatics Research & Innovation.
3 Senior Researcher, 9 Songdomirae-ro, Yeonsu-gu, Incheon 21988, International Center for Urban Water Hydroinformatics Research & Innovation.
4 Director, 9 Songdomirae-ro, Yeonsu-gu, Incheon 21988, International Center for Urban Water Hydroinformatics Research & Innovation.
1 Researcher, 9 Songdomirae-ro, Yeonsu-gu, Incheon 21988, International Center for Urban Water Hydroinformatics Research & Innovation. E-mail: ektha7677@gmail.com
2 Researcher, 9 Songdomirae-ro, Yeonsu-gu, Incheon 21988, International Center for Urban Water Hydroinformatics Research & Innovation.
3 Senior Researcher, 9 Songdomirae-ro, Yeonsu-gu, Incheon 21988, International Center for Urban Water Hydroinformatics Research & Innovation.
4 Director, 9 Songdomirae-ro, Yeonsu-gu, Incheon 21988, International Center for Urban Water Hydroinformatics Research & Innovation.
Received January 1, 2023; Revised March 2, 2023; Accepted March 2, 2023.
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
- Abstract
- This study analyzed annual issues of urban flood damage articles using the Latent Dirichlet allocation technique. As a result of the analysis, major issues in urban flood damage include collapse of facilities due to landslides and river flooding, inflow of soil and damage due to flooding in the low-lying areas of the Imjin river, inflow of soil and damage to farmlands and houses, and damage to houses, vinyl houses, and vehicles due to landslides. The declaration of a special disaster area was drawn due to the accident that occurred and the large flood damage in agricultural and residential areas. In this study, a methodology for developing a technique for utilizing press data related to urban flooding was presented through text mining-based collection of news articles on urban flood damage and natural language processing.
- Keywords : Big data, latent Dirichlet assignment, LDA, topic modeling. Web Crawling
Full Text(PDF) Free
