Results for the fake news challenge have been announced. The system we submitted was an ensemble of 5 student classifiers written for the Sheffield University COM6513 Natural Language Processing MSc module. Our team came 11th overall – out of 50 submissions. Because the module deadline was so close to the FNC deadline, we didn’t have […]
With the continued growth of misinformation and the looming European and British election there is an ever-growing need to automatically fact-check publications. There’s been some news coverage regarding the work my supervisor and I have been conducting: Nieman Foundation for Journalism at Harvard, New York Times.
Today we announce the baseline accuracy for the fake news challenge and provide code which allows the public to reproduce and build-upon the features/classifier to improve the scores on the hold-out test set. Target to beat: 79.52% Learn more about the Fake News Challenge: http://fakenewschallenge.org Code is available on GitHub: https://github.com/FakeNewsChallenge/fnc-1-baseline