FemaRepViz: Automatic extraction and geo-temporal visualization of FEMA national situation updates

Chi Chun Pan, Prasenjit Mitra

Research output: Chapter in Book/Report/Conference proceedingConference contribution

12 Citations (Scopus)

Abstract

An architecture for visualizing information extracted from text documents is proposed. In conformance with this architecture, a toolkit, FemaRepViz, has been implemented to extract and visualize temporal, geospatial, and summarized information from FEMA National Update Reports. Preliminary tests have shown satisfactory accuracy for FEMARepViz. A central component of the architecture is an entity extractor that extracts named entities like person names, location names, temporal references, etc. FEMARepViz is based on FactXtractor, an entity-extractor that works on text documents. The information extracted using FactXtractor is processed using GeoTagger, a geographical name disambiguation tool based on a novel clustering-based disambiguation algorithm. To extract relationships among entities, we propose a machine-learning based algorithm that uses a novel stripped dependency tree kernel. We illustrate and evaluate the usefulness of our system on the FEMA National Situation Updates. Daily reports are fetched by FEMARepViz from the FEMA website, segmented into coherent sections and each section is classified into one of several known incident types. We use ConceptVista, Google Maps and Google Earth to visualize the events extracted from the text reports and allow the user to interactively filter the topics, locations, and time-periods of interest to create a visual analytics toolkit that is useful for rapid analysis of events reported in a large set of text documents.

Original languageEnglish (US)
Title of host publicationVAST IEEE Symposium on Visual Analytics Science and Technology 2007, Proceedings
Pages11-18
Number of pages8
DOIs
StatePublished - Dec 1 2007
EventVAST IEEE Symposium on Visual Analytics Science and Technology 2007 - Sacramento, CA, United States
Duration: Oct 30 2007Nov 1 2007

Publication series

NameVAST IEEE Symposium on Visual Analytics Science and Technology 2007, Proceedings

Other

OtherVAST IEEE Symposium on Visual Analytics Science and Technology 2007
CountryUnited States
CitySacramento, CA
Period10/30/0711/1/07

Fingerprint

Visualization
Learning systems
Websites
Earth (planet)

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Computer Science Applications

Cite this

Pan, C. C., & Mitra, P. (2007). FemaRepViz: Automatic extraction and geo-temporal visualization of FEMA national situation updates. In VAST IEEE Symposium on Visual Analytics Science and Technology 2007, Proceedings (pp. 11-18). [4388991] (VAST IEEE Symposium on Visual Analytics Science and Technology 2007, Proceedings). https://doi.org/10.1109/VAST.2007.4388991
Pan, Chi Chun ; Mitra, Prasenjit. / FemaRepViz : Automatic extraction and geo-temporal visualization of FEMA national situation updates. VAST IEEE Symposium on Visual Analytics Science and Technology 2007, Proceedings. 2007. pp. 11-18 (VAST IEEE Symposium on Visual Analytics Science and Technology 2007, Proceedings).
@inproceedings{4dfd6d89f44047058203e8eebc23ec51,
title = "FemaRepViz: Automatic extraction and geo-temporal visualization of FEMA national situation updates",
abstract = "An architecture for visualizing information extracted from text documents is proposed. In conformance with this architecture, a toolkit, FemaRepViz, has been implemented to extract and visualize temporal, geospatial, and summarized information from FEMA National Update Reports. Preliminary tests have shown satisfactory accuracy for FEMARepViz. A central component of the architecture is an entity extractor that extracts named entities like person names, location names, temporal references, etc. FEMARepViz is based on FactXtractor, an entity-extractor that works on text documents. The information extracted using FactXtractor is processed using GeoTagger, a geographical name disambiguation tool based on a novel clustering-based disambiguation algorithm. To extract relationships among entities, we propose a machine-learning based algorithm that uses a novel stripped dependency tree kernel. We illustrate and evaluate the usefulness of our system on the FEMA National Situation Updates. Daily reports are fetched by FEMARepViz from the FEMA website, segmented into coherent sections and each section is classified into one of several known incident types. We use ConceptVista, Google Maps and Google Earth to visualize the events extracted from the text reports and allow the user to interactively filter the topics, locations, and time-periods of interest to create a visual analytics toolkit that is useful for rapid analysis of events reported in a large set of text documents.",
author = "Pan, {Chi Chun} and Prasenjit Mitra",
year = "2007",
month = "12",
day = "1",
doi = "10.1109/VAST.2007.4388991",
language = "English (US)",
isbn = "9781424416592",
series = "VAST IEEE Symposium on Visual Analytics Science and Technology 2007, Proceedings",
pages = "11--18",
booktitle = "VAST IEEE Symposium on Visual Analytics Science and Technology 2007, Proceedings",

}

Pan, CC & Mitra, P 2007, FemaRepViz: Automatic extraction and geo-temporal visualization of FEMA national situation updates. in VAST IEEE Symposium on Visual Analytics Science and Technology 2007, Proceedings., 4388991, VAST IEEE Symposium on Visual Analytics Science and Technology 2007, Proceedings, pp. 11-18, VAST IEEE Symposium on Visual Analytics Science and Technology 2007, Sacramento, CA, United States, 10/30/07. https://doi.org/10.1109/VAST.2007.4388991

FemaRepViz : Automatic extraction and geo-temporal visualization of FEMA national situation updates. / Pan, Chi Chun; Mitra, Prasenjit.

VAST IEEE Symposium on Visual Analytics Science and Technology 2007, Proceedings. 2007. p. 11-18 4388991 (VAST IEEE Symposium on Visual Analytics Science and Technology 2007, Proceedings).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - FemaRepViz

T2 - Automatic extraction and geo-temporal visualization of FEMA national situation updates

AU - Pan, Chi Chun

AU - Mitra, Prasenjit

PY - 2007/12/1

Y1 - 2007/12/1

N2 - An architecture for visualizing information extracted from text documents is proposed. In conformance with this architecture, a toolkit, FemaRepViz, has been implemented to extract and visualize temporal, geospatial, and summarized information from FEMA National Update Reports. Preliminary tests have shown satisfactory accuracy for FEMARepViz. A central component of the architecture is an entity extractor that extracts named entities like person names, location names, temporal references, etc. FEMARepViz is based on FactXtractor, an entity-extractor that works on text documents. The information extracted using FactXtractor is processed using GeoTagger, a geographical name disambiguation tool based on a novel clustering-based disambiguation algorithm. To extract relationships among entities, we propose a machine-learning based algorithm that uses a novel stripped dependency tree kernel. We illustrate and evaluate the usefulness of our system on the FEMA National Situation Updates. Daily reports are fetched by FEMARepViz from the FEMA website, segmented into coherent sections and each section is classified into one of several known incident types. We use ConceptVista, Google Maps and Google Earth to visualize the events extracted from the text reports and allow the user to interactively filter the topics, locations, and time-periods of interest to create a visual analytics toolkit that is useful for rapid analysis of events reported in a large set of text documents.

AB - An architecture for visualizing information extracted from text documents is proposed. In conformance with this architecture, a toolkit, FemaRepViz, has been implemented to extract and visualize temporal, geospatial, and summarized information from FEMA National Update Reports. Preliminary tests have shown satisfactory accuracy for FEMARepViz. A central component of the architecture is an entity extractor that extracts named entities like person names, location names, temporal references, etc. FEMARepViz is based on FactXtractor, an entity-extractor that works on text documents. The information extracted using FactXtractor is processed using GeoTagger, a geographical name disambiguation tool based on a novel clustering-based disambiguation algorithm. To extract relationships among entities, we propose a machine-learning based algorithm that uses a novel stripped dependency tree kernel. We illustrate and evaluate the usefulness of our system on the FEMA National Situation Updates. Daily reports are fetched by FEMARepViz from the FEMA website, segmented into coherent sections and each section is classified into one of several known incident types. We use ConceptVista, Google Maps and Google Earth to visualize the events extracted from the text reports and allow the user to interactively filter the topics, locations, and time-periods of interest to create a visual analytics toolkit that is useful for rapid analysis of events reported in a large set of text documents.

UR - http://www.scopus.com/inward/record.url?scp=47349093410&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=47349093410&partnerID=8YFLogxK

U2 - 10.1109/VAST.2007.4388991

DO - 10.1109/VAST.2007.4388991

M3 - Conference contribution

AN - SCOPUS:47349093410

SN - 9781424416592

T3 - VAST IEEE Symposium on Visual Analytics Science and Technology 2007, Proceedings

SP - 11

EP - 18

BT - VAST IEEE Symposium on Visual Analytics Science and Technology 2007, Proceedings

ER -

Pan CC, Mitra P. FemaRepViz: Automatic extraction and geo-temporal visualization of FEMA national situation updates. In VAST IEEE Symposium on Visual Analytics Science and Technology 2007, Proceedings. 2007. p. 11-18. 4388991. (VAST IEEE Symposium on Visual Analytics Science and Technology 2007, Proceedings). https://doi.org/10.1109/VAST.2007.4388991