Identification of disaster-affected areas using exploratory visual analysis of georeferenced Tweets: application to a flood event

V. Cerutti, Georg Fuchs, Gennady Andrienko, Natalia Andrienko, F.O. Ostermann

Research output: Contribution to conferencePaperAcademicpeer-review

Abstract

To enable decision makers to conduct a rapid assessment of the situation during the disaster response phase and improve situational awareness, we propose an approach to identify affected areas using geo-spatial footprints. These geo-spatial footprints summarize information and threats and are derived from georeferenced social media messages and authoritative data sources. The combination of data mining techniques for data pre-processing and exploratory visual analysis is a promising approach for dealing with heterogeneous data under time pressure. This paper presents the first steps towards this objective by using georeferenced Tweets to define the geospatial footprint of a flood event that occurred in Italy in 2013. After cleaning the data, density-based clustering, distance-bounded spatio-temporal event clustering and data-driven territory tessellation techniques were applied; visual analysis was used to define the best parameters combination. A comparison between the results and ground-truth data was performed. The proposed methods showed positive results in the identification of areas affected by the flood at regional scale. The combination of data mining with visual analysis for parameters setting proved to be an intuitive and fast procedure that could help decision makers deal with geosocial media data and assist them with rapid assessment of the situation
Original languageEnglish
Number of pages5
Publication statusPublished - 2016
Event19th AGILE conference on Geographic Information Science, AGILE 2016 - Helskini, Finland
Duration: 14 Jun 201617 Jun 2016
Conference number: 19

Conference

Conference19th AGILE conference on Geographic Information Science, AGILE 2016
Abbreviated titleAGILE
CountryFinland
CityHelskini
Period14/06/1617/06/16

Fingerprint

visual analysis
disaster
footprint
data mining

Keywords

  • Twitter
  • Disaster Management
  • geospatial footprint
  • Data Mining
  • visual analytics
  • ITC-GOLD

Cite this

Cerutti, V., Fuchs, G., Andrienko, G., Andrienko, N., & Ostermann, F. O. (2016). Identification of disaster-affected areas using exploratory visual analysis of georeferenced Tweets: application to a flood event. Paper presented at 19th AGILE conference on Geographic Information Science, AGILE 2016, Helskini, Finland.
Cerutti, V. ; Fuchs, Georg ; Andrienko, Gennady ; Andrienko, Natalia ; Ostermann, F.O. / Identification of disaster-affected areas using exploratory visual analysis of georeferenced Tweets: application to a flood event. Paper presented at 19th AGILE conference on Geographic Information Science, AGILE 2016, Helskini, Finland.5 p.
@conference{98dfe9f4e95b4f04beebcf7cadb0f7b0,
title = "Identification of disaster-affected areas using exploratory visual analysis of georeferenced Tweets: application to a flood event",
abstract = "To enable decision makers to conduct a rapid assessment of the situation during the disaster response phase and improve situational awareness, we propose an approach to identify affected areas using geo-spatial footprints. These geo-spatial footprints summarize information and threats and are derived from georeferenced social media messages and authoritative data sources. The combination of data mining techniques for data pre-processing and exploratory visual analysis is a promising approach for dealing with heterogeneous data under time pressure. This paper presents the first steps towards this objective by using georeferenced Tweets to define the geospatial footprint of a flood event that occurred in Italy in 2013. After cleaning the data, density-based clustering, distance-bounded spatio-temporal event clustering and data-driven territory tessellation techniques were applied; visual analysis was used to define the best parameters combination. A comparison between the results and ground-truth data was performed. The proposed methods showed positive results in the identification of areas affected by the flood at regional scale. The combination of data mining with visual analysis for parameters setting proved to be an intuitive and fast procedure that could help decision makers deal with geosocial media data and assist them with rapid assessment of the situation",
keywords = "Twitter, Disaster Management, geospatial footprint, Data Mining, visual analytics, ITC-GOLD",
author = "V. Cerutti and Georg Fuchs and Gennady Andrienko and Natalia Andrienko and F.O. Ostermann",
year = "2016",
language = "English",
note = "19th AGILE conference on Geographic Information Science, AGILE 2016, AGILE ; Conference date: 14-06-2016 Through 17-06-2016",

}

Cerutti, V, Fuchs, G, Andrienko, G, Andrienko, N & Ostermann, FO 2016, 'Identification of disaster-affected areas using exploratory visual analysis of georeferenced Tweets: application to a flood event' Paper presented at 19th AGILE conference on Geographic Information Science, AGILE 2016, Helskini, Finland, 14/06/16 - 17/06/16, .

Identification of disaster-affected areas using exploratory visual analysis of georeferenced Tweets: application to a flood event. / Cerutti, V.; Fuchs, Georg ; Andrienko, Gennady; Andrienko, Natalia; Ostermann, F.O.

2016. Paper presented at 19th AGILE conference on Geographic Information Science, AGILE 2016, Helskini, Finland.

Research output: Contribution to conferencePaperAcademicpeer-review

TY - CONF

T1 - Identification of disaster-affected areas using exploratory visual analysis of georeferenced Tweets: application to a flood event

AU - Cerutti, V.

AU - Fuchs, Georg

AU - Andrienko, Gennady

AU - Andrienko, Natalia

AU - Ostermann, F.O.

PY - 2016

Y1 - 2016

N2 - To enable decision makers to conduct a rapid assessment of the situation during the disaster response phase and improve situational awareness, we propose an approach to identify affected areas using geo-spatial footprints. These geo-spatial footprints summarize information and threats and are derived from georeferenced social media messages and authoritative data sources. The combination of data mining techniques for data pre-processing and exploratory visual analysis is a promising approach for dealing with heterogeneous data under time pressure. This paper presents the first steps towards this objective by using georeferenced Tweets to define the geospatial footprint of a flood event that occurred in Italy in 2013. After cleaning the data, density-based clustering, distance-bounded spatio-temporal event clustering and data-driven territory tessellation techniques were applied; visual analysis was used to define the best parameters combination. A comparison between the results and ground-truth data was performed. The proposed methods showed positive results in the identification of areas affected by the flood at regional scale. The combination of data mining with visual analysis for parameters setting proved to be an intuitive and fast procedure that could help decision makers deal with geosocial media data and assist them with rapid assessment of the situation

AB - To enable decision makers to conduct a rapid assessment of the situation during the disaster response phase and improve situational awareness, we propose an approach to identify affected areas using geo-spatial footprints. These geo-spatial footprints summarize information and threats and are derived from georeferenced social media messages and authoritative data sources. The combination of data mining techniques for data pre-processing and exploratory visual analysis is a promising approach for dealing with heterogeneous data under time pressure. This paper presents the first steps towards this objective by using georeferenced Tweets to define the geospatial footprint of a flood event that occurred in Italy in 2013. After cleaning the data, density-based clustering, distance-bounded spatio-temporal event clustering and data-driven territory tessellation techniques were applied; visual analysis was used to define the best parameters combination. A comparison between the results and ground-truth data was performed. The proposed methods showed positive results in the identification of areas affected by the flood at regional scale. The combination of data mining with visual analysis for parameters setting proved to be an intuitive and fast procedure that could help decision makers deal with geosocial media data and assist them with rapid assessment of the situation

KW - Twitter

KW - Disaster Management

KW - geospatial footprint

KW - Data Mining

KW - visual analytics

KW - ITC-GOLD

UR - https://ezproxy2.utwente.nl/login?url=https://webapps.itc.utwente.nl/library/2015/conf/cerutti_ide.pdf

M3 - Paper

ER -

Cerutti V, Fuchs G, Andrienko G, Andrienko N, Ostermann FO. Identification of disaster-affected areas using exploratory visual analysis of georeferenced Tweets: application to a flood event. 2016. Paper presented at 19th AGILE conference on Geographic Information Science, AGILE 2016, Helskini, Finland.