The Election Oracle: Internet Polls Get Serious?
November 9, 2010 § Leave a comment
For the past two months, The Daily Beast has been trying to figure out a way to use internet polling to its advantage, especially during election season. We all know that internet polls are pretty unreliable—user anonymity, double isps, multiple voting, etc… However, the Beast decided to try something new, an Election Oracle:
“Specifically, the Oracle began perpetually scanning 40,000 websites, message boards, and forums, as well as Twitter and other public social media feeds (private networks like Facebook remained off-limits, and every public comment was tabulated anonymously), took the millions of political comments we found each day and sorted them by candidate. The Oracle specifically studied the exact text of each comment, and figured out if was positive, negative, neutral, or mixed. This plus/minus factor, using a 10-day moving average, was then mixed with traditional polling to create a prediction.”
And whaddya know, the Oracle miffed only one of the 37 Senate races (Harry Reid v. Sharron Angle). The House race didn’t fare quite as well, but it seems like there is a lot of potential for honing down this way of “polling” in order to make a more precise prediction. This also presents another creative use of social media in relation to politics.