Can Twitter Predict Election Winners?

A new study suggests Twitter can be predictive of election results.

The Atlantic looks at research from Indiana University that finds the more times a Congressional candidate was mentioned on Twitter before an election, the better that candidate did at the polls.

The study specifically controlled for the conditions surrounding an election. If a candidate is an incumbent, they would be mentioned on Twitter more, so the study discounted their position. Likewise, the study also discounted candidates who the press covered more, using the number of times a candidate’s name was mentioned on CNN as an imprecise measurement of mainstream media hype.

The study’s finding bears a number of implications. First, it implies that all Twitter chatter is good Twitter chatter: that if more people are talking about you, you’re likely to do better at the polls. Second, it provides a working model for predictive Twitter analysis in future elections, especially in the US.

However, Roll Call’s Stuart Rothenblog isn’t convinced by the predictive power of Twitter.

Since House re-election rates have been over 90 percent in 19 of the past 23 elections, you don’t need polls or tweet counts to predict the overwhelming majority of race outcomes. In most cases, all you need to know is incumbency (or the district’s political bent) and the candidates’ parties to predict who will win.

So, it’s possible that tweet counts simply reflect — and are a function of — existing name recognition, which is crucial in races where one candidate has it and the other doesn’t.