Big Buzz On Twitter Means Better Chances On Election Day : NPR


Big Buzz On Twitter Means Better Chances On Election Day : NPR

I’m a member of the American Association for Public Opinion Research, the professional association for pollsters and this story has been burning up the email list over the last 24 hours. A couple of cogent points made by other folks (I won’t mention their names, as I don’t think the list is for publication), and one of my own.

1. There seems to be some confusion over the roll that polling and pollsters play in modern political campaigns. It’s not simply predicting the outcome of an election, which is not terribly difficult in and of itself. A poll, no matter how accurate, conducted the day before an election or after the fact is of no use to political strategist.

2. There also seems to be some confusion over the meaning of “margin of error.”

3. This point is original to me, the main difference is that polls allow you to gauge attitudes with a battery of questions and determine where correlations exist between attitudes or demographic information and vote choice. I don’t know how you could do that with Twitter alone.

4. Finally, this is related to point number one above, and I wrote about this in a comment on Mark Blumenthal’s Mystery Pollster blog in his early days on the web, but the actual techniques for polling are not as important as the experience and expertise that a professional pollster brings to the table every campaign he or she works. If a pollster is wildly off more times than not but always gives his candidate advice that leads to a win, that pollster is more valuable than one who correctly predicts the outcome of the election but is powerless to suggest to a campaign strategist, manager or candidate how to affect the outcome in a way favorable to the candidate.

Twitter and social media may provide new or additional data points, and may be useful for some other things to pollsters. But ultimately, the expertise that comes from plumbing the minds of voters over the course of years is irreplaceable to modern campaigns.


Is the political poll a 20th century dinosaur lumbering toward extinction to the accompaniment of triumphant tweets? Well, a team at Indiana University says you can predict election results just as well by mining Twitter for the names of candidates as you can by polling. They examined a sample of just over a half a billion tweets from August through October 2010. And joining us to talk about what they found, from New York, where the research was presented today to the American Sociological Association, is Fabio Rojas, associate professor of sociology at Indiana University. Welcome.

FABIO ROJAS: Thank you very much. It’s a pleasure to be here.

SIEGEL: And you’re saying that the candidates with the most buzz in the Twitter-verse also win at the ballot box?

ROJAS: Roughly speaking, yes, more tweets does give you more votes.

SIEGEL: And does it predict the margin of victory pretty well?

ROJAS: In many cases, it does. It tends to do very well when the race is very competitive. For example, there was one in Utah where, you know, somebody was getting about 47 percent of the vote and the Twitter share was about 45 percent of the vote. So a lot of the cases are within the margin of error of a traditional poll.

The cases where the margin of error is big are cases where the race itself is not very competitive, where somebody’s running against a very weak competitor.

[T]his is going to transform the polling industry because what this shows is that anybody with a laptop computer can come up with the forecast of an election that may be on par or better as a traditional poll.

via Big Buzz On Twitter Means Better Chances On Election Day : NPR.

Comments ( 1 )
  • says:

    Right. Traditional polling is certainly a more accurate means of assessing voters’ views than a “twitter poll” would be, but might the latter be a more reliable tool than the former when it comes to getting a handle of voters’ feelings?

    Also, please continue to throw cold water on all this “more tweets = more votes” malarkey. It’s such a snake oil…