Twitter is good for finding information, for sure. But could it be used to predict events ahead of time?

Could you use Twitter to ostensibly figure out that a historical tide is shifting before it actually does? Kinda. This is from a new study done by a PhD student at MIT named Nathan Kallus. Here’s the abstract:

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. We present efforts to predict the occurrence, specific timeframe, and location of such actions before they occur based on public data collected from over 300,000 open content web sources in 7 languages, from all over the world, ranging from mainstream news to government publications to blogs and social media. 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.

The ultimate summary is this line:

The study validates and quantifies the common intuition that data on social media (beyond mainstream news sources) are able to predict major events.

This is an interesting concept, because I always felt the next tier of technology would be predictive. In a space like medicine, the only real purpose of technology — besides summarizing data quickly, I suppose — would be predictive, in the sense of trying to figure out potential risks, how an illness might spread, etc. But I think the next big wave of technology is going to be predictive in the sense of supermarkets knowing where to channel you, or even, as this study suggests, being able to use Twitter to say, “Something big is about to happen in Poland” or something of the like. I think Twitter is predominantly a tool for journalists anyway, and if there was a demonstrated capability to figure out “the next big story” before everyone’s reporting it, that would make things pretty interesting on there.

There’s still more work to be done, but the trend line here is towards using Twitter to predict news, disease outbreaks, even stock market fluctuations. If that happens, the real value of the service would seemingly only rise.

Ted Bauer