Attensity Election Forecasts
March 14, 2012
Is the prediction half right or half wrong? Sci-Tech Today seems to opt for optimism with “Twitter Analysis Gets Elections Half Right.” Attensity attempted to demonstrate its social analytics chops by forecasting Super Tuesday Republican Primary results using Twitter tweets. Their predictions were about 50% accurate; isn’t that about what you’d get flipping coins?
A lack of location data seems to be the reason Attensity’s predictions were less precise than hoped. Writer Scott Martin reveals:
Part of the problem lies in a lack of location-based data about Twitter users’ tweets. Such information is ‘scarce’ on Twitter, says Michael Wu, principal scientist of analytics for Lithium, a social-analytics firm. That’s because Twitter users would have to turn on the ‘location’ feature in their mobile devices. A vast pool of location-based tweets would enable analytics experts to better connect tweets to where they come from across the nation. In the case of Super Tuesday, that would mean more localized information on tweets about candidates.
Another roadblock to accurate prediction lies in identifying when multiple tweets come from the same enthusiastic tweeter, or are spam-like robo-tweets. Furthermore, there is no ready way to correlate the expression of opinions with actions, like actually voting. It seems that this analytic process has a long way to go. It also seems that half right is close enough to spin marketing horseshoes.
Serving several big-name clients, Attensity provides enterprise-class social analytics as well as industry solutions for vertical markets. They pride themselves on the accuracy and ease of use of their tools. My thought is that I will pick horses the old fashioned way.
Cynthia Murrell, March 14, 2012
Sponsored by Pandia.com
Comments
-
- Subscribe to Beyond Search
Feature archive
News archive
-
