Twitter is great for things like spoiling the Olympics. But can the social network's data-gathering ways be used to predict big, potentially world-shaking events, like mass protests, for example?
The short answer, according to a new study, is a resounding "sometimes." Nathan Kallus, a PhD student at the Massachusetts Institute of Technology, analyzed thousands of tweets associated with the 2013 coup in Egypt, and claims that the social unrest associated with it was, in fact, predictable ahead of time.
For his research, Kallus mined data from more than 300,000 public information sources, including news sites like the New York Times, countless blogs, and—of course—social media to predict crowd behavior.
"With public information becoming widely accessible and shared on today's web, greater insights are possible into crowd actions by citizens and non-state actors such as large protests and cyber activism," he writes. Makes sense: If protesters in Egypt used social media to physically mobilize their efforts, something like Twitter could provide a hazy window into potential history.
Using natural language processing, event information is extracted from content such as type of event, what entities are involved and in what role, sentiment and tone, and the occurrence time range of the event discussed. Statements made on Twitter about a future date from the time of posting prove particularly indicative. We consider in particular the case of the 2013 Egyptian coup d'etat. The study validates and quantifies the common intuition that data on social media (beyond mainstream news sources) are able to predict major events.
One major caveat, of course, is that this study had the luxury of peering backwards into 2013. And Twitter, as it stands, still hasn't been used to accurately predict an event in the future. Kallus's experiment does however present an interesting thesis, but we'll still have to see if Twitter's robust data gathering can indeed provide an accurate crystal ball into the future. "We're not there yet," Haile Owusu, director of research at SocialFlow, told Fast Company last July, "and one has to wonder if it's even possible."