Tracking media reports on the Shiga toxin-producing Escherichia coli O104: H4 outbreak in Germany

Abstract

In May 2011, an outbreak of enterohemorrhagic Escherichia coli (EHEC) occurred in northern Germany. The Shiga toxin-producing strain O104:H4 infected several thousand people, frequently leading to haemolytic uremic syndrome (HUS) and gastroenteritis (GI). First reports about the outbreak appeared in the German media on Saturday 21st of May 2011; the media attention rose to high levels in the following two weeks, with up to 2000 articles categorized per day by the automatic threat detection system MedISys (Medical Information System). In this article, we illustrate how MedISys detected the sudden increase in reporting on E. coli on 21st of May and how automatic analysis of the reporting provided epidemic intelligence information to follow the event. Categorization, filtering and clustering allowed identifying different aspects within the unfolding news event, analyzing general media and official sites in parallel. © 2012 ICST Institute for Computer Science, Social Informatics and Telecommunications Engineering.