Welcome to European Tribune. It's gone a bit quiet around here these days, but it's still going.

Facebook effect on poll turn-out: How significant?

by marco Wed Sep 12th, 2012 at 09:05:15 PM EST

I need sharper analytical minds than mine to help assess the significance of some findings just published in Nature: A 61-million-person experiment in social influence and political mobilization:

The results showed that those who got the informational message voted at the same rate as those who saw no message at all. But those who saw the social message were 2% more likely to click the 'I voted' button and 0.3% more likely to seek information about a polling place than those who received the informational message, and 0.4% more likely to head to the polls than either other group.

Facebook Experiment Found to Boost U.S. Voter Turnout, Scientific American

What I couldn't get was the "0.4% more likely to head to the polls than either other group":  how is that significant?

The Scientific American article continues:

The social message, the researchers estimate, directly increased turnout by about 60,000 votes. But a further 280,000 people were indirectly nudged to the polls by seeing messages in their news feeds, for example, telling them that their friends had clicked the 'I voted' button. "The online social network helps to quadruple the effect of the message," says Fowler.

On the other hand, a CNN article "340,000 votes may have come from Facebook message" notes:

All in all, between the direct and indirect effects found in the study, the total percentage increase per person in voting behavior as a result of a Facebook News Feed message is about 2.2%. That's on the lower end of the spectrum compared to what other "get out the vote" studies have found with regards to other means of communication.

The Nature study has preview images of some charts, but as I don't have a subscription, I can't access the full-size images:

At the end of the CNN article, Professor James Fowler of the UCSD Medical Genetics Division, adds a few other points that also complicate the picture:

But the real effect could be even greater than what the study observed, Fowler said. A lot of people who saw the message had probably already voted, through early voting and absentee ballots - in fact, one-third of voters in the 2010 election cast their votes before Election Day.

Many people who saw the message were also unable to vote because they logged into Facebook too late in the day to go to their local polling station - as high as 20% may have been in this situation, Fowler said. Also, younger people are less likely to vote, and are less susceptible to such appeals, he said.

"I think if you added all of these things up, we'd find that this was actually one of the stronger `get out the vote' messages that we've seen in the literature," he said.

Two authors of the paper, Adam D. I. Kramer & Cameron Marlow, are from Facebook's Data Science division that posted about the study on their Facebook page.

The Nature study pages says:

Competing financial interests
The authors declare no competing financial interests.

But color me a little skeptical -- and a lot confused -- about the numerical significance of these results.

What I couldn't get was the "0.4% more likely to head to the polls than either other group":  how is that significant?

If you have 61000000 data points, 0.4% could be very significant.

by njh on Thu Sep 13th, 2012 at 12:55:22 AM EST
How do you know that the people who clicked "I voted" actually voted ? As opposed to just clicking it to impress their pals

keep to the Fen Causeway
by Helen (lareinagal at yahoo dot co dot uk) on Thu Sep 13th, 2012 at 10:53:29 AM EST

Go to: [ European Tribune Homepage : Top of page : Top of comments ]