AI-powered fake news spotter under development at ASU

The algorithm, which is especially useful during a health crisis, is being developed to scrutinize news being shared on social media and alert users to misinformation.
fact checking
(Getty Images)

Researchers at Arizona State University this week announced work underway to develop artificial intelligence software that can detect fake news and help prevent the spread of disinformation.

The algorithm, called Defend, is being developed by ASU professor Huan Liu and doctoral student Kai Shu to scrutinize news being shared on social media and warn consumers of its potential falseness.

“The idea of Defend is to create a transparent fake news detection algorithm for decision-makers, journalists and stakeholders to understand why a machine learning algorithm makes such a prediction,” Shu said in an interview with 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.

“One example is if one piece of fake news is claiming that the president is giving citizenship to some Iranians but this is a false claim, and we find a user comment talking about some additional evidence, such as, ‘The president does not have the power to give citizenship,’ then this can help explain why this news is fake,” Shu said.

The ability to spot fake news and disinformation is especially critical during the current pandemic to help people get critical health information and ensure they’re not misinformed by fake news, Shu said.

“In the COVID-19 scenarios, there is a lot of misleading information and fake news, mostly about the public health domain,” he said. “We should be more diligent when we consume information online and be careful of the fact that not all information is genuine, and also be aware that we can be easily fooled.”

A recent video shared on social media, for example, made false claims that the coronavirus was “intentionally released.”


Researchers at other universities have taken similar approaches to prevent the spread of fake news online; Duke University students developed a fact-checking program called FactStream, to verify the statements made by President Donald Trump during his 2019 State of the Union speech. Like ASU’s algorithm, FactStream is still in its development phase but researchers said they believe the technology is promising.

Betsy Foresman

Written by Betsy Foresman

Betsy Foresman was an education reporter for EdScoop from 2018 through early 2021, where she wrote about the virtues and challenges of innovative technology solutions used in higher education and K-12 spaces. Foresman also covered local government IT for StateScoop, on occasion. Foresman graduated from Texas Christian University in 2018 — go Frogs! — with a BA in journalism and psychology. During her senior year, she worked as an intern at the Center for Strategic and International Studies in Washington, D.C., and moved back to the capital after completing her degree because, like Shrek, she feels most at home in the swamp. Foresman previously worked at Scoop News Group as an editorial fellow.

Latest Podcasts