Skip to main content

New academic tool used to identify fake news domain names

(Image credit: Shutterstock)

Academic researchers have created a new machine learning tool that can identify when a domain name has been created purely to spread misinformation, ensuring it can be stopped before it has had a chance to disseminate ‘fake news’.

Real-Time Prediction of Online False Information Purveyors and their Characteristics, a working paper written by Anil Doshi from the UCL School of Management, Sharat Raghavan of the University of California, Berkley and William Schmidt from Cornell University, details how false information domains can be identified rapidly.

The early detection method uses a combination of the domain registration data that is available when a website is established and browser behavior to identify whether a site is likely to go on to produce false information. Traits like whether the registering party is kept private and if a site has been set up around the time of a newsworthy event are also taken into consideration.

“Many models that predict false information use the content of articles or behaviors on social media channels to make their predictions,” Doshi commented. “By the time that data is available, it may be too late. These producers are nimble and we need a way to identify them early. By using domain registration data, we can provide an early warning system using data that is arguably difficult for the actors to manipulate. Actors who produce false information tend to prefer remaining hidden and we use that in our model.”

Lies travel fast

The machine learning tool was able to correctly identify 92% of all false information domains and 96.2% of non-false information domains set up in relation to the 2016 US election before they began operations. Given that malicious actors have been increasingly leveraging major events to spread misinformation, the tool could be of huge value to online regulators.

In addition, it could help with the creation of a safer internet. Fake news is sometimes used by threat actors to spread malware, tempting online users to click on dubious links that actually inject malicious software into their device. Stopping misinformation could block a potential exploit.