A new study has revealed that feeding news articles in a supercomputer could help predict revolutions and other major world events.
According to BBC News, Kalev Leetaru, from the University of Illinois' Institute for Computing in the Humanities, Arts and Social Science fed close to around 100 million news article dating back to as far as 1945 into a supercomputer, which then rightly predicted the recent Arab unrest.
The researcher used the data from US government’s Open Source Centre and BBC Monitoring. The study also used New York Times articles going back to 1945.
The data which was collected was fed into a SGI Altix supercomputer, known as Nautilus, which is housed at the University of Tennessee.
The researchers analysed the news articles for two main pieces of information. One was ‘Mood’, which looked for words like "terrible", "horrific" or "nice", to determine whether particular news was good or bad.
The second information that researcher analysed was location, which included the location where the event took place and the location of the people involved in the news.
"Monitoring these qualitative aspects of news coverage provides substantial benefits over the traditional quantitative political science event database approach. An event database can only capture that a bombing took place, but a church bombing in one country might result only in condemnations, while in another it might push it over the edge to revolt," said Leetaru.