Mining Web Data for Epidemiological Surveillance

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...). The experiments conducted on a real corpora (AFP news) showed a precision greater than 94% and an F-measure above 85%. We also investigate the interest of tacking into account the data collected through social networks such as Twitter to trigger alarms.