What social media data could tell us about the future
Northeastern’s Alessandro VespigÂnani, SternÂberg Family DisÂtinÂguished UniÂverÂsity ProÂfessor of physics, comÂputer sciÂence, and health sciÂences, has teamed up with an interÂdisÂciÂpliÂnary group of sciÂenÂtists to develop an innoÂvÂaÂtive method to map how tweets about large- scale social events spread.
Using masÂsive twitter datasets and sophisÂtiÂcated quanÂtiÂtative meaÂsures, it tracks how inforÂmaÂtion about politÂical protests, large busiÂness acquiÂsiÂtions, and other “colÂlecÂtive pheÂnomena†gather momentum, peak, and fall over time, from city to city, and where the impetus comes from for that trajectory.
The findÂings, pubÂlished Friday in the journal Science Advances, is only a first step, notes coauÂthor Nicola Perra, a former research assoÂciate at Northeastern’s NetÂwork SciÂence InstiÂtute. But knowing the charÂacÂterÂisÂtics of that buildup could, in the future, enable us to preÂpare ahead of time for undeÂsirÂable reperÂcusÂsions from such events, with impliÂcaÂtions for crises from earthÂquakes to power- grid failures.
“A lot of people have anaÂlyzed social media in terms of the volume of tweets regarding parÂticÂular pheÂnomena such as the Arab Spring,†says VespigÂnani, who is also the director of the NetÂwork SciÂence InstiÂtute. “What we are trying to underÂstand is the presÂence of preÂcurÂsors: Can we find a signal in the flow of inforÂmaÂtion that will tell us someÂthing big is about to happen? That’s the multimillion- dollar question.â€
In an interÂdisÂciÂpliÂnary leap, the researchers turned to netÂwork modÂeling in neuÂroÂscience to conÂduct the study. “For the brain we map based on physÂiÂology, and for social aggreÂgates, like those in this paper, we map on geogÂraphy,†says Vespignani.
In neuÂroÂscience netÂwork modÂeling, the “nodes,†or cenÂters of activity, are funcÂtional brain areas–say, the motor cortex, which is responÂsible for movement–and the “links†conÂnecting the nodes are neural cirÂcuits. For example, the cirÂcuits conÂnecting the motor cortex to the audiÂtory cortex, which is responÂsible for hearing, trace a neural pathway, or “link,†that enables us to tap our foot to a beat and even dance.
In this new, social- events study, the nodes are cities–for example, Madrid and Barcelona in the researchers’ analysis of twitter transÂmisÂsion during the 2011 Spanish anti- austerity movement–and the links are the pathÂways the tweets take over time.
ConÂsider the Spanish protest, which later sparked the Occupy Wall St. moveÂment in the U.S. The tweets gained in volume and intenÂsity until, says VespigÂnani, they reached a “social tipÂping point of colÂlecÂtive pheÂnomÂenon†on May 20, 2011. “You create a system that starts from a few nodes that then drive others, and so on, until everyÂbody is talking to everyÂbody else in a full coorÂdiÂnaÂtion of the inforÂmaÂtion,†he explains.
The quanÂtiÂtaÂtive idenÂtiÂfiÂcaÂtion of those driÂvers sets this new method apart from other approaches to tracking social media, says Perra, who is now a senior lecÂturer at London’s UniÂverÂsity of GreenÂwich. “It enables us to underÂstand which city is driÂving the conÂverÂsaÂtion when and to charÂacÂterize the dynamics of the spread.â€
“Before you can develop a method to preÂdict future events,†he adds, “you need a quanÂtiÂtaÂtive underÂstanding of the comÂmuÂnicaÂtion patÂterns that shaped past events.â€
Laying the groundÂwork for preÂdicÂtive studies is what VespigÂnani and his colÂleagues are attempting to do with this analysis of five major social events: the 2011 protest in Spain; the 2013 protest in Brazil, known as the “Brazilian Autumnâ€; the release of a HolÂlyÂwood blockÂbuster in 2012; and Google’s acquiÂsiÂtion of Motorola in 2014.
“Everyone wants to preÂdict when the next big event is going to be, what will trend in the future,†says Perra. “We are, as a research comÂmuÂnity, in the early stages of underÂstanding this type of pheÂnomena. There is very little underÂstanding of even past events, so we are very far from preÂdicÂtion. But in the future our findÂings may lead us to that.â€
###