Computing Veracity – the Fourth Challenge of Big Data

RumourEval: open evaluation of rumour systems

We’ve had a task accepted at the long-running SemEval workshop, on rumour evaluation. This is a shared task, meaning that anyone can enter their rumour detection systems. Tasks at previous SemEvals have really helped advance the state of the art. For our task, which’ll be held next year, we’ll use Pheme data and methods to supply a big pile of practice data helping people build their systems, and also create a new set of data around some event from this year, which will be used to judge how good systems are at the end.

Training data and a task website will be launched over the summer, and then there are 6-9 months of time until everyone has to submit their systems’ evaluations of the final data. We’re excited about being able to offer this task, and it’s been really interesting for the community, too!


Be Sociable, Share!

Comments are currently closed.