Twitter Can’t Yet Predict Elections
By Stuart Rothenberg Posted at 5 a.m. Aug. 14
The folks over at the Washington Post must have needed copy desperately for Monday’s opinion page if they were willing to publish a piece titled, “How Twitter can help predict an election.”
In the column, Indiana University Sociologist Fabio Rojas asserts: “Twitter discussions are an unusually good predictor of U.S. House elections.” He and his fellow researchers “found a strong correlation between a candidate’s ‘tweet share’ and the final two-party vote share,” and it doesn’t even matter whether the tweets are positive or negative. Content is irrelevant.
If you believe that, would you be interested in buying the Brooklyn Bridge from me? I have a sale on it this week only.
Rojas asserts that he and his co-authors of a new paper “predicted the winner in 404 out of 406 competitive races” after looking at more than 500,000 tweets that mentioned Republican and Democratic candidates for Congress in 2010.
Normally, when political scientists or journalists write about “competitive” races they are talking about contests where at least two candidates have at least some chance of victory. Obviously, there weren’t 406 “competitive” House races in 2010 under that definition — at the Rothenberg Political Report, we rated just more than 100 House races as “not safe,” and a far fewer number in the truly competitive categories — so Rojas must be using the term to describe contested races.
Most races aren’t real competitions, of course. Relatively few House challengers run robust campaigns, and voters generally are unfamiliar with challengers.
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.
via Twitter Can’t Yet Predict Elections | Rothenblog.







Comments ( 0 )