What does Twitter have to say about politics?

Here’s another Twitter-​​analysis post for all you net­work sci­ence junkies out there.

And although I’m a bit late to the table (New Sci­en­tist reported on this a week ago) I couldn’t resist.

Bruno Gonçalves, a postdoc in Alessandro Vespig­nani’s research group here at North­eastern, and three col­leagues at Indiana Uni­ver­sity expanded their research on par­tisan Twitter net­works with a paper to be pub­lished in the open-​​access journal EPJ Data Sci­ence (where Vespig­nani is a co-​​editor in chief).

The team looked at Tweets from over 18,000 Twitter users during the 18 week period leading up to the 2010 midterm elec­tion. They sep­a­rated the users into “left-​​leaning” or “right-​​leaning” groups based on their use of polit­ical hash­tags like #tcot (top con­ser­v­a­tives on twitter) and #p2 (Pro­gres­sives 2.0). The “sub­strate” net­work is defined by follow rela­tion­ships and shows how the two par­tisan groups keep to them­selves. This isn’t new, Gonçalves’ team and others have shown sim­ilar results pre­vi­ously. I blogged about it not too long ago, actu­ally.

What is sur­prising is that the activ­i­ties within the seg­re­gated groups are rather unex­pected based on the social-​​media activ­i­ties of right– and left– leaning groups leading up to the 2008 pres­i­den­tial elec­tion. Back then, according to the article “the Obama cam­paign enjoyed twice as much web traffic, had four times as many YouTube viewers and five times more Face­book friends com­pared to the McCain campaign.”

In 2010, the right-​​leaning crowd took the social-​​media lead, at least on Twitter. The team found that, com­pared to left-​​wingers, right-​​wingers are more likely to self-​​identify as such in their bios, spend more time talking about pol­i­tics on Twitter and do so more often, as well as share more politically-​​related infor­ma­tion in the form of hyperlinks.

The right wing group is more tightly inter­con­nected, has a larger net­work of politically-​​minded fol­lowers and has “a higher degree of engage­ment with the Twitter plat­form itself.”

Finally, they used self-​​reported loca­tion data (as opposed to geolo­ca­tion data) to deter­mine where the groups are Tweeting from, geo­graph­i­cally speaking. While there is some overlap between the Twitter map and polit­ical party maps, the team accounts for the dis­crep­ancy by saying that per­haps out­liers in a polit­i­cally homoge­nous com­mu­nity turn to Twitter for their dis­course, which seems like a rea­son­able enough expla­na­tion to me.

What I’m still con­fused about though, is how much this means about the polit­ical con­ver­sa­tion as a whole. Couldn’t it be that left-​​leaners are more active on Face­book, for instance, instead of Twitter? What does it mean to have an active Twitter com­mu­nity when there are sev­eral other types of com­mu­ni­ties out there…like for instance the so-​​called “grass roots” com­mu­nity which may have once been called people-​​talking-​​to-​​each-​​other-​​in-​​real-​​life.

I’m new to the Twit­ter­sphere and quickly real­izing how pow­erful a tool it is for infor­ma­tion dis­sem­i­na­tion. So pow­erful that it scared me away for years before my boss (Hi Lucy!) said I had to get on it. But while Twitter could be a good pre­dictor of total polit­ical com­mu­ni­ca­tion behav­iors, I’m not sure whether we’ve proved that yet. Maybe you know.

Anyway, all of this is based on the 2010 elec­tion and I’m get­ting really excited to see what comes out of the net­work sci­ence labs regarding the upcoming pres­i­den­tial election.