Advertisement

QAnon founder may have been identified thanks to machine learning

Researchers believe two men were the primary authors of posts attributed to Q.

Cheney Orr / reuters

With help from machine learning software, computer scientists may have unmasked the identity of Q, the founder of the QAnon movement. In a sprawling report published on Saturday, The New York Times shared the findings of two independent teams of forensic linguists who claim they’ve identified Paul Furber, a South African software developer who was one of the first to draw attention to the conspiracy theory, as the original writer behind Q. They say Arizona congressional candidate Ron Watkins also wrote under the pseudonym, first by collaborating with Furber and then later taking over the account when it eventually moved to post on his father’s 8chan message board.

The two teams of Swiss and French researchers used different methodologies to come to the same conclusion. The Swiss one, made up of two researchers from startup OrphAnalytics, used software to break down Q’s missives into patterns of three-character sequences. They then tracked how often those sequences repeated. The French team, meanwhile, trained an AI to look for patterns in Q’s writing. Both techniques broadly fall under an approach known as stylometry that looks to analyze writing in a way that is measurable, consistent and replicable. To avoid the possibility of confusing their respective programs, the teams limited their analysis to social media posts. Among all the other possible authors they put through the test, they say the writing of Furber and Watkins stood out the most for how similar it was that of Q’s.

And they’re confident in that identification. The French team made of computational linguists Florian Cafiero and Jean-Baptiste Camps told The Times their software correctly identified Furber’s writing in 98 percent of tests and Watkins’ in 99 percent. “At first most of the text is by Furber,” said Cafiero. “But the signature of Ron Watkins increased during the first few months as Paul Furber decreased and then dropped completely.”

People have previously used machine learning software to identify Harry Potter author J.K. Rowling as the secret writer of Cuckoo’s Calling, a 2013 crime fiction novel Rowling wrote under the pseudonym Robert Galbraith. More broadly, law enforcement agencies have successfully used stylometry in a variety of criminal cases, including by the FBI to show that Ted Kaczynski was the Unabomber.

Experts The Times spoke to – including Professor Patrick Juola, the computer scientist who identified Rowling as the author of Cuckoo’s Calling – told they found the findings credible and persuasive. “What’s really powerful is the fact that both of the two independent analyses showed the same overall pattern,” Juola said.

Both Furber and Watkins deny they wrote any of Q’s messages. “I am not Q,” the latter told The Times. Furber, meanwhile, said he was influenced by Q’s posts to change the style of his prose, a claim linguistic experts told the outlet was “implausible.” Also worth mentioning is the fact the analysis included tweets from Furber that date from the earliest days of Q’s existence.

What happens next is unclear. The researchers who worked on the identification told The Times they hope unmasking Q will loosen QAnon’s hold on people. Spreading like wildfire on social media, the conspiracy theory has had a profound effect on politics in the US and other parts of the world. And while Q hasn’t posted a new message since the end of 2020, that hasn’t dampened people’s enthusiasm for conspiracies about the "deep state" and its involvement in their lives.