^
A
A
A

Supercomputer is able to predict large-scale social events in the world

 
, medical expert
Last reviewed: 16.10.2021
 
Fact-checked
х

All iLive content is medically reviewed or fact checked to ensure as much factual accuracy as possible.

We have strict sourcing guidelines and only link to reputable media sites, academic research institutions and, whenever possible, medically peer reviewed studies. Note that the numbers in parentheses ([1], [2], etc.) are clickable links to these studies.

If you feel that any of our content is inaccurate, out-of-date, or otherwise questionable, please select it and press Ctrl + Enter.

10 September 2011, 12:55

The supercomputer is able to predict major events in the world arena based on the analysis of news reports.

This is the conclusion of the study, authored by Kalev Leetaru, an employee of the Institute for Computation in the Humanities and Sociology of the University of Illinois.

He set up an experiment in which the supercomputer analyzed millions of newspaper articles and messages from other sources, and then gave out forecasts of changes in the social atmosphere in various countries around the world.

This system predicted a change in the situation in Libya and Egypt, and also recorded indications of the possible location of Osama bin Laden.

Despite the fact that this system worked retrospectively, the scientist believes that it can be easily applied to predict future conflicts.

"Nautilus" gives the forecast

Information that came to the computer SGI Altix, known as the "Nautilus" at the University of Tennessee, was taken from a number of sources, including from reports of the BBC Monitoring Service.

The news agency reports, as well as the New York Times archive since 1946, have also been analyzed.

In general, Kalev Leetaru used more than 100 million articles.

They were analyzed in two ways: moods - whether bad or good news was reported in this article, as well as the place where the events took place.

The key words in the first case were "terrible", "disgusting", "excellent." Site analysis or "geocoding" took into account the mention of geographical names, for example, Cairo, and applied them as a coordinate point on the world map.

An analysis of the message elements was also carried out, during which a map of 100 trillion logical interrelations arose.

Supercomputer "Nautilus", based on 1004 nuclear processors such as Intel Nehalem, is capable of performing 8.2 trillion operations per second.

He issued various schedules for each of the countries where there was a so-called "Arab spring".

In each case, the computer recorded a noticeable deterioration of the public atmosphere on the eve of the outbreak of unrest, both in the country itself and outside it.

In the case of Egypt, a month before the resignation of Hosni Mubarak, the degree of public discontent reached a mark that was observed only twice in the last 30 years.

According to Leetar, his system gives more accurate forecasts of the development of the social situation than the forecasts that the US intelligence services prepared for the US government.

"The fact that the US president spoke in support of Mubarak shows that even the analysis at the highest level indicated that Mubarak will stay in power," Kalev Leetaru said. "This is probably due to the fact that such an analysis is conducted by experts who spent 30 years to study Egypt, and for 30 years with Mubarak nothing happened. "

Similar changes in public sentiment were noted by the computer retrospectively in the case of Libya and conflicts in the Balkans in the 90s.

In search of bin Laden

In his article Kalev Leetaru suggests that such an analysis of all information about Osama bin Laden could give an indication of his whereabouts.

Despite the fact that many believed that the leader of Al-Qaeda is in Afghanistan, the geographical data obtained from the analysis of news sources persistently pointed to his stay in northern Pakistan.

Only in one communication was mentioned the city of Abbotabad, in which bin Laden took refuge.

However, geocoding, conducted with the help of the Nautilus computer, narrowed the search area to 200 km.

As Dr. Leetaru says, his system is very similar in terms of operating principles to existing algorithms for predicting changes in stock markets.

It is easy to adapt to the analysis of future events, and it is able to work in real time.

"The next stage will be testing the system at the city level to investigate the interaction of various groups of the population," the scientist said.

trusted-source[1]

You are reporting a typo in the following text:
Simply click the "Send typo report" button to complete the report. You can also include a comment.