Analyzing Fake Content on Twitter During Boston Marathon Bombings ~Patrick Meier, iRevolution

Posted on October 21, 2013 By

One of the biggest challenges we face here at DisasterMap.net is establishing Real Time Situational Awareness during disaster.  I’ve been known to go days without sleep to stay Live on top of different hurricane, flood, wildfire and tornado events. But, we also have our company infrastructure set up to go mobile if necessary in order to maintain online presence during, for example, hurricanes here in New Orleans, LA. –as Katrina and Rita did in fact wipe out the electrical grid and cell networks for hundreds of miles in 2005.

We didn’t really have Twitter when 80% of New Orleans flooded because 3 Corps of Engineers badly designed and built floodwalls failed at half load. Yet, it wouldn’t have mattered anyway without the cell towers or electrical grid. The ASCE and Corps got out ahead of the story within a week, and the Major News Media followed, and said Katrina over-topped our flood-walls. That statement turned out to be a deliberate PR lie. If only Dr. Bob Bea had had a Twitter Account! The Federal Flood of New Orleans 8-29-05 put me on a long road home, and onto the internet. Yet it was the misnaming, the myth-framing of it as a Natural Disaster that led me to start this business of Disaster Mapping.

I found Twitter about the 3rd year into the interregnum, and shortly thereafter found Patrick Meier and his wonderful Disaster Geography/Crisis Mapping blog iRevolution: “As iRevolution readers already know, the application of Information Forensics to social media is one of my primary areas of interest. So I’m always on the lookout for new and related studies, such as this one (PDF), which was just published by colleagues of mine in India.

iRevolution-Tweets-table1-gupta-et-alThe study by Aditi Gupta et al. analyzes fake content shared on Twitter during the Boston Marathon Bombings earlier this year. Gupta et al. collected close to 8 million unique tweets posted by 3.7 million unique users between April 15-19th, 2013. The table above provides more details. The authors found that rumors and fake content comprised 29% of the content that went viral on Twitter, while 51% of the content constituted generic opinions and comments. The remaining 20% relayed true information. Interestingly, approximately 75% of fake tweets were propagated via mobile phone devices compared to true tweets which comprised 64% of tweets posted via mobiles.” Read more.

Information ForensicsTwitter     , , , , , , , , , , , ,


Leave a Reply