News headlines used to predict future events

0
386

This article was first published on BBC News

Researchers have developed software which analyses old headlines to predict news
Researchers have developed software which analyses old headlines to predict news

Researchers have developed software which could predict future events such as disease outbreak.

The prototype software uses a combination of archive material from the New York Times and data from other websites, including Wikipedia.

The experts focused on predicting riots, deaths and disease outbreaks and say their accuracy was between 70%-90%.

The work is a collaboration between Microsoft Research and the Technion-Israel Institute of Technology.

In their research paper, the two scientists say that using a mixture of archived news reports and real-time data, they were able to see links between droughts and storms in parts of Africa and cholera outbreaks.

For example in 1973 the New York Times published news of a drought in Bangladesh, and in 1974 it reported a cholera epidemic.

Following reports of another drought in the same country in 1983, the newspaper again reported cholera deaths in 1984.

“Alerts about a downstream risk of cholera could have been issued nearly a year in advance,” wrote researchers Eric Horvitz, director of Microsoft Research, and Kira Radinsky, PhD student at Technion-Israel Institute of Technology.

While other research has been done in this area, it has tended to be retrospective – looking back at the event leading up to an outbreak – rather than using that data to try to look ahead to the next one, they said.

Ms Radinsky told MIT Technology Review that other useful websites included knowledge bases DBpedia and OpenCyc, and language database Word.

The software could also be used to verify the likelihood of other predictions, according to the research paper.

“It can be valuable to identify situations where there is a significantly lower likelihood of an event than expected by experts based on the large set of observations and feeds being considered in an automated manner,” it said.

“”I truly view this as a foreshadowing of what’s to come,” Mr Horvitz told MIT Technology Review.

“Eventually this kind of work will start to have an influence on how things go for people.”