Epimining: Using Web News for Influenza Surveillance

Didier Breton 1 Sandra Bringay 2, 3 François Marques 1 Pascal Poncelet 2 Mathieu Roche 4
2 TATOO - Fouille de données environnementales
LIRMM - Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier
4 TEXTE - Exploration et exploitation de données textuelles
LIRMM - Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier
Abstract : Epidemiological surveillance is an important issue of public health policy. In this paper, we describe a method based on knowledge extraction from news and news classification to understand the epidemic evolution. Descriptive studies are useful for gathering information on the incidence and characteristics of an epidemic. New approaches, based on new modes of mass publication through the web, are developed: based on the analysis of user queries or on the echo that an epidemic may have in the media. In this study, we focus on a particular media: web news. We propose the Epimining approach, which allows the extraction of information from web news (based on pattern research) and a fine classification of these news into various classes (new cases, deaths, and so forth). The experiments conducted on a real corpora (AFP news) showed a precision greater than 94% and an F-measure above 85%.
Complete list of metadatas

Cited literature [8 references]  Display  Hide  Download

https://hal-lirmm.ccsd.cnrs.fr/lirmm-00723582
Contributor : Mathieu Roche <>
Submitted on : Friday, August 10, 2012 - 10:49:04 PM
Last modification on : Thursday, June 6, 2019 - 2:38:05 PM
Long-term archiving on : Sunday, November 11, 2012 - 2:30:35 AM

File

Breton_DMHM2012_final.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : lirmm-00723582, version 1

Citation

Didier Breton, Sandra Bringay, François Marques, Pascal Poncelet, Mathieu Roche. Epimining: Using Web News for Influenza Surveillance. DMHM: Data Mining for Healthcare Management, May 2012, Kuala Lumpur, Malaysia. pp.11-21. ⟨lirmm-00723582⟩

Share

Metrics

Record views

255

Files downloads

293