The Meedan Blog Archive

Two verification reports: Analyzing Fake Content and Identifying Eyewitness Reporters

As we endeavor to keep our finger firmly on the pulse of all things related to social media verification and crowdsourced fact checking, we keep a close eye on hundreds of feeds using Google Reader The Old Reader. One particularly rich vein of verification nuggets can be found over on the blog of our good friend Patrick Meier, "iRevolution". A couple of recent reports that Patrick has shared have caught our eye:

$1.00 per RT #BostonMarathon #PrayForBoston: Analyzing Fake Content on Twitter (Aditi Gupta, Hemank Lamba, Ponnurangam Kumaraguru)

iRevolution summary Full Report


Learning from the Crowd: Collaborative Filtering Techniques for Identifying On-the-Ground Twitterers during Mass Disruptions (Kate Starbird, Grace Muzny, Leysia Palen)

iRevolution summary Full Report

Patrick has done an excellent job summarizing both reports: Gupta et al looks at how fake content spread spread on Twitter in the hours and days following the Boston Marathon bombings of 2013, with particularly interesting findings on the role of fake accounts in misinformation, and the way verified and supposedly authoritative accounts play a key role in propagating fake content; Starbird et al examines an ambitious and exciting automized mechanism for identifying Twitter accounts providing eyewitness testimony from on the ground. It's great to see such high quality research being carried out in this emergent field, and we look forward to seeing more such work in future.