The Journal of Machine Learning Research
Modern Information Retrieval
Towards personalized learning to rank for epidemic intelligence based on social media streams
Proceedings of the 21st international conference companion on World Wide Web
Epidemic intelligence: for the crowd, by the crowd
ICWE'12 Proceedings of the 12th international conference on Web Engineering
| Hi-index | 0.00 |
In the presence of sudden outbreaks, how can social media streams be used to strengthen surveillance capacity? In May 2011, Germany reported one of the largest described outbreaks of Enterohemorrhagic Escherichia coli (EHEC). The Shiga toxin-producing strain O104:H4 infected several thousand people, frequently leading to haemolytic uremic syndrome (HUS) and gastroenteritis (GI). By the end of June, 47 persons had died. In this work, we study the crowd's behavior in Twitter during the outbreak. In particular, we present how Twitter can be exploited to support Epidemic Intelligence (EI) in the tasks of early warning, signal assessment and outbreak investigation. A user study with experts from the Robert Koch Institute, Germany's national-level public health authority, and from Lower Saxony State Health Department (NLGA) provide important insights towards the realization of an open early warning system based on Twitter, helping to realize the vision of Epidemic Intelligence for the Crowd, by the Crowd.