PITTSBURGH, May 18 (UPI) — U.S. researchers say they analyzed a billion Twitter messages and found sentiments expressed in the tweets were similar to those in public opinion polls.
Carnegie Mellon University scientists said the tweets sent during 2008 and 2009 yielded measures of consumer confidence and of presidential job approval similar to those of well-established polling services. That finding, the researchers said, suggests analyzing the text found in streams of tweets could become a cheap, rapid means of gauging public opinion on at least some subjects.
Assistant Professor Noah Smith, who led the study, said the tools for extracting public opinion from social media text are still crude and social media remain in their infancy, meaning the extent to which such methods could replace or supplement traditional polling is still unknown.
“With 7 million or more messages being tweeted each day, this data stream potentially allows us to take the temperature of the population very quickly,” Smith said. “The results are noisy, as are the results of polls. Opinion pollsters have learned to compensate for these distortions, while we’re still trying to identify and understand the noise in our data. Given that, I’m excited that we get any signal at all from social media that correlates with the polls.”
The study will be presented next week in Washington during a meeting of the Association for the Advancement of Artificial Intelligence’s International Conference on Weblogs and Social Media.
Copyright 2010 United Press International, Inc. (UPI). Any reproduction, republication, redistribution and/or modification of any UPI content is expressly prohibited without UPI’s prior written consent.