Hari Seldon, I Presume? Supercomputer Predicts Revolutions

We live in a science fiction world. The high tech future of Star Trek is a part of our everyday lives in things like cell phones and Bluetooth headsets. But there are some scifi advances that still feel far off. Until this morning I thought psychohistory was one of them.

Psychohistory is a science created by Isaac Asimov in his Foundation novels. Hari Seldon, the man who dreamed it up, figured that, much like subatomic particles, it’s impossible to predict what any one human would do but that given enough information he could predict what humanity would do. Using a series of equations, Seldon was able to see the upcoming fall of the Galactic Empire and put into action a plan to save humanity from the millenia of barbarism that followed.

There’s something great about the concept of psychohistory; there’s comfort in the predictability of societies. And Seldon wasn’t just a passive observer of the future - he set up multiple Foundations in order to attempt to guide humanity to a golden age.

But psychohistory is fiction. For now. A recent experiment with the supercomputer Nautilus showed that it might be possible to predict upcoming revolutions and social upheavals. Here’s what they did, according to the BBC:

The study’s information was taken from a range of sources including the US government-run Open Source Centre, and the Summary of World Broadcasts (now known as 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, [they] 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.

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.

The program was able to accurately show massive dips in public sentiment just before the uprisings in countries that are experiencing the ‘Arab Spring’ of revolutions. Of course this was all retroactive - the study was done after the events had happened, but the results are still remarkable. It looks like the program can give a heads up about massive social events about to come.

There’s still a long, long way to go before we’re predicting events a thousand years out, but it’s a start. What’s funny is that I’m sure the CIA has had a supercomputer doing exactly  this for some time now…