What if there were a way to automatically identify credible tweets during major events like disasters? Sounds rather far-fetched, right? Think again.
The new field of Digital Information Forensics is increasingly making use of Big Data analytics and techniques from artificial intelligence like machine learning to automatically verify social media. This is how my QCRI colleague ChaTo et al. already predicted both credible and non-credible tweets generated after the Chile Earthquake (with an accuracy of 86%). Meanwhile, my colleagues Aditi, et al. from IIIT Delhi also used machine learning to automatically rank over 35 million tweets generated during more than a dozen major international events including the UK Riots and the Libya Crisis. So we teamed up with Aditi et al. to turn those academic findings into TweetCred, a free app that identifies credible tweets automatically.
We’ve just launched the very first version of TweetCred—key word being first. This means that our new app is…
View original post 505 more words