AI-powered fake news spotter under development at ASU

By using data sets of fact-checked news pieces that are understood to be false, as well some that are confirmed to be true, the machine-learning algorithm can be trained to predict what new information is likely fake and part of an attempt to spread disinformation, according to the researchers.

The algorithm also attempts to give users an explanation of why certain news is flagged as fake by analyzing the news content, as well as comments on the news posts.

via edscoop.com

I don’t see how this could work, but it has to be better than Politifact.