17 Nov '12, 9am

The Peering column in the Nov-Dec issue of IEEE IC has published an essay by me on Twitter & Elections. Find it here:

Predicting X from Twitter is a popular fad within the Twitter research subculture. It seems both appealing and relatively easy. Among such studies, electoral prediction is maybe the most attractive, and a growing body of literature exists on this topic. This research problem isn't only interesting, but is also extremely difficult. However, most authors seem to be more interested in claiming positive results than in providing sound and reproducible methods. It's also especially worrisome that recent papers seem to only acknowledge those studies supporting the idea that Twitter can predict elections. This is all problematic because while simple approaches are purported to be good enough, the predictive power of Twitter regarding elections has been greatly exaggerated, and difficult research problems still lie ahead.

Full article: http://www.computer.org/csdl/mags/ic/2012/06/mic201206009...

Tweets

#peakoil Did oil decide the last three American...

energybulletin.net 18 Nov '12, 6pm

Was the most recent American election outcome determined by the presidential debates, changing demographics, voter views o...

Why A Website Is More Important Than Facebook & Twitter

Why A Website Is More Important Than Facebook &...

smallbusinesssem.com 18 Nov '12, 10pm

Why A Website Is More Important Than Facebook & Twitter Matt McGee | November 18, 2012 | 0 Comments I don’t know John Burk...

#peakoil Did oil decide the last three American...

peakoil.com 18 Nov '12, 5pm

Was the most recent American election outcome determined by the presidential debates, changing demographics, voter views o...