Global Disease Monitoring and Forecasting with Wikipedia

Infectious disease remains costly in human and economic terms. Effective and timely disease surveillance is a critical component of prevention and mitigation strategies. The limitations of traditional disease surveillance systems have motivated new techniques based upon internet data sources such as search queries and social media. However, 4 challenges remain before internet-based disease surveillance models can be reliably integrated into an operational system: openness, breadth, transferability, and forecasting. We evaluated a new data source, Wikipedia access logs, in these 4 challenges for global disease surveillance and forecasting

Objective

To explore the use of Wikipedia as a data source for disease surveillance.