Monday, 12 September 2011

SGI Supercomputer to predict future revolutions…Hmmm | Looseword

According to an article by the BBC, US Researchers claim that feeding News Stories into a Supercomputer could predict future world events.  The study was based on millions of news articles relating to Libya and Egypt and although the information was retrospective, it is believed that in the future if the same process is used the computer will be able to predict trends which will give indications of events such as those which occurred in  Libya and Egypt.

The system also picked up early clues about Osama Bin Laden’s location.

(BBC) Kalev Leetaru, from the University of Illinois’ Institute for Computing in the Humanities, Arts and Social Science, presented his findings in the journal First Monday.

Mood and location

The study’s information was taken from a range of sources including the US government-run Open Source Centre and BBC Monitoring, both of which monitor local media output around the world.

News outlets which published online versions were also analysed, as was the New York Times‘ archive, going back to 1945.

In total, Mr Leetaru gathered more than 100 million articles.

Reports were analysed for two main types of information: mood – whether the article represented good news or bad news, and location – where events were happening and the location of other participants in the story.

The Nautilus SGI supercomputer crunched the 100 million articles

Mood detection, or “automated sentiment mining” searched for words such as “terrible”, “horrific” or “nice”.

Location, or “geocoding” took mentions of specific places, such as “Cairo” and converted them in to coordinates that could be plotted on a map.

Analysis of story elements was used to create an interconnected web of 100 trillion relationships.

Predicting trouble

Data was fed into an SGI Altix supercomputer, known as Nautilus, based at the University of Tennessee.

The machine’s 1024 Intel Nehalem cores have a total processing power of 8.2 teraflops (trillion floating point operations per second).

Based on specific queries, Nautilus generated graphs for different countries which experienced the “Arab Spring”.

In each case, the aggregated results of thousands of news stories showed a notable dip in sentiment ahead of time – both inside the country, and as reported from outside

This is all very well but does it take into consideration criminal acts such as that of NATO in destabilising a country by inducing unrest with agents on the ground?


Share this:

Like this:

Be the first to like this post.