Researchers at Los Alamos National Laboratory in New Mexico say that tracking Wikipedia page views can forecast the spread of influenza and dengue fever.
The researchers claim their algorithm allows them to overcome the challenges that hamper the reliability of other similar data surveillance methods based on Internet information.
Google Flu Trends, is a web service operated by Google, which provides estimates of influenza activity by aggregating Google search queries. But, early last year it was reported that they drastically overestimated peak flu levels, casting some doubt on the search giant’s ability to predict flu trends.
“Using simple statistical techniques, our proof-of-concept experiments suggest that these data are effective for predicting the present, as well as forecasting up to the 28-day limit of our tests,” the Los Alamos researchers say. “Our results also suggest that these models can be used even in places with no official data upon which to build models.
Though there are still detractors to the notion of using such systems to predict disease outbreaks, it is no doubt amazing to witness the many uses to which the growing volumes of meta data available on the internet will be used.
Read the full report here.