acm-header
Sign In

Communications of the ACM

ACM TechNews

Tool Uses AI to Flag Fake News for Media Fact-Checkers


View as: Print Mobile App Share:
The researchers were motivated to develop the tool by the proliferation of online posts and news stories fabricated to deceive or mislead readers.

A new artificial intelligence tool could help social media networks and news organizations screen out fake news.

Credit: University of Waterloo News (CA)

Researchers at the University of Waterloo in Canada have developed an artificial intelligence tool that could help social media networks and news organizations screen out fake news.

The tool employs deep learning algorithms to ascertain whether assertions made in posts or stories are backed by other posts and stories on the same topic, with 90% accuracy.

Waterloo's Alexander Wong said the tool can augment the capabilities of human fact-checkers by flagging information “that doesn’t look quite right for verification. It isn’t designed to replace people, but to help them fact-check faster and more reliably.”

Said Waterloo’s Chris Dulhanty, “We need to empower journalists to uncover truth and keep us informed. This represents one effort in a larger body of work to mitigate the spread of disinformation.”

From University of Waterloo News (CA)
View Full Article

 

Abstracts Copyright © 2019 SmithBucklin, Washington, DC, USA


 

No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account