Forecasting the News

Software Predicts Tomorrow’s News by Analyzing Today’s and Yesterday’s
Technology Review (02/01/13) Tom Simonite

Researchers at Microsoft and the Technion-Israel Institute of Technology have developed software that predicts when and where disease outbreaks might occur, based on 22 years of New York Times articles and other online data. Microsoft’s Eric Horvitz says the system could help aid organizations be more proactive in fighting epidemics or other problems. In tests involving forecasts of diseases, violence, and significant numbers of deaths, the system’s warnings were correct 70-90 percent of the time. The performance is good enough to suggest that a more refined version could be used in real settings, for example, to assist experts at government aid agencies involved in planning humanitarian response and readiness, Horvitz notes. “One source we found useful was DBpedia, which is a structured form of the information inside Wikipedia constructed using crowdsourcing,” says Technion-Israel researcher Kira Radinsky. “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.” The information used to create the predictions provides context that is not available in news articles, and which is necessary to determine the general rules for which events precede others.

View Full Article

Leave a Reply

Your email address will not be published. Required fields are marked *

Comment moderation is enabled. Your comment may take some time to appear.