A doctoral student at Indiana University says counting tweets in an election can be used to predict results.
Using the Indiana Twitter database, which contains the largest sample of tweets in the world available to academic researchers, he analyzed more than 500 million tweets from the U.S. House races for 2010 and 2012.
"Think of this as a measurement of buzz," said Fabio Rojas, an associate professor of sociology in the College of Arts and Sciences at IU Bloomington. "We call this the 'all publicity is good publicity' finding. Even if you don't like somebody, you would only talk about them if they're important."