Researchers are tapping into the web to predict the future. 

We've seen these initiatives before with doctors using Google and Twitter to track flu outbreaks. But now Eric Horvitz of Microsoft Research and Kira Radinsky of the Technion-Israel Institute have gone one step farther, creating software that digs deep into 22 years of the New York Times' archives, Wikipedia and 90 or so other web resources.

“I truly view this as a foreshadowing of what’s to come,” Horvitz told the MIT Technology Review. “Eventually this kind of work will start to have an influence on how things go for people.”

In his newly released paper, "Mining the Web to Predict Future Events," Horvitz explains how the web might serve as a crystal ball. Not only does it function as a vast repository of information, he writes, the software he created with Radinsky can work tirelessly to identify patterns, and has "more comprehensive access to stories" that might otherwise stay under the radar. For example, everyday stories that seem to carry no real significance might prove to be the missing link for a recurring trend, like the cholera outbreak in Rwanda. 

In turn, this information can be used to predict riots, deaths and disease outbreaks—and perhaps one day even prevent them. 

[via Giga Om]