The project for my M.Sc. this summer is going to be about tracking disease trends through blog posts. This will mostly likely be tracking Influenza as it is the most common disease each year and has readily available data, especially in the US, though I hope to include the UK and other countries if I can too. I’m not sure how reliable or accurate this is going to be, but there’s only one way to find out.
Tracking disease trends through indirect measurements is starting to become quite an interesting area in research. The internet has a vast number of users and small lag time between events and publication which makes projects such as Google Flu possible to accurately predict trends faster than direct means.
New social and conversational websites such as Twitter and Facebook also bring a lot more data directly posted from users in an almost real time basis that could improve disease tracking even more if the data is use in the right way. With website like these still being quite closed with their data for commercial, privacy, and technical issues it is still away off before researchers can go further with this.
I’m going to post my progress on this blog as the project develops to try and be as open with this research as possible with the hope that it can be applied to other sources of data than I have access to.