Mining Social Media and Web Searches For Disease Detection

Yang, Y. Tony; Horneffer, Michael; DiLisio, Nicole

The rapid identification of an outbreak of an infectious disease is necessary to more promptly and effectively develop public health responses. The Canadians were among the first to pioneer the development of web-based surveillance technologies. In the 1990s, Health Canada created the Global Public Health Intelligence Network. 5 The network uses autonomous news feed aggregators based on established search queries to collect articles containing relevant information about the possibility of a public health emergency. 5 The Canadian network was particularly useful during the 2002 outbreak of severe acute respiratory syndrome (SARS) in the Guangdong Province of China, as well as the 2008 Canadian listeriosis outbreak. In the case of SARS in China, the network identified the outbreak more than two months before the World Health Organization publically published details on cases of the new respiratory illness. 5 With regards to the listeriosis outbreak in Canada, the network indicated a statistically significant spike in the pattern of listeriosis-related searches nearly a month before the declaration of the outbreak. 5 In both cases, the network-based intelligence predicted a public health crisis before it was officially declared. The data the network obtained was derived from the searches conducted by individuals accessing social media on the Internet.