Predictive Analysis Progress
March 6, 2013
Using data analysis to predict the future, a feat naturally called predictive analysis, is an intriguing facet of the analysis prism. GMA News takes a look at some progress on such software in, “New Software Can Predict Future News.” I suppose “new” is in the eye of the beholder; Recorded Future has been doing this for a couple of years now.
This article, though, covers research performed by Microsoft and the Technion-Israel Institute of Technology. Working with twenty-two years’ worth of New York Times articles and other information online, researchers have been testing ways of using this data to predict outbreaks of disease, violence, and other sources of significant mortality. Grim subject matter, to be sure, but imagine if we could take steps to deflect or minimize such occurrences before they happen. The article informs us:
“The system uses 22 years of New York Times archives, from 1986 to 2007, as well as data from the Internet to learn about what leads up to major news events. [Technion-Israel ‘s Kira]Radinsky said one useful source was DBpedia, a structured form of the information inside Wikipedia constructed using crowdsourcing. Other sources included WordNet, which helps software understand the meaning of words, and OpenCyc, a database of common knowledge. ‘We can understand, or see, the location of the places in the news articles, how much money people earn there, and even information about politics,’ Radinsky said. With all this information, researchers get valuable context not available in news articles, and which is necessary to figure out general rules for what events precede others.”
It appears that this project is far from complete, and Microsoft has formed no plans to bring it to market, according to Eric Horvitz of the Microsoft team. The article does acknowledge Recorded Future‘s work in this area, noting their strong customer base within the intelligence community.
Who can predict when the rest of us will get the chance to give this compelling technology a whirl?
Cynthia Murrell, March 06, 2013
Sponsored by ArnoldIT.com, developer of Augmentext
Comments
2 Responses to “Predictive Analysis Progress”
Predictive modeling is a very interesting area for #textanalytics and #BigData http://t.co/2Nrs0ey2rM
Predictive Analysis Progress – http://t.co/GhEh3NLE3S