[ad_1]
GENEVA: The mysterious “Q” behind the QAnon conspiracy movement, which was instrumental in the assault on the United States Capitol, is in fact two people, according to Swiss experts.
Swiss startup OrphAnalytics said it had used its algorithm-based machine learning text analysis software, developed to detect plagiarism, to help unravel the mystery behind QAnon.
“There are clearly two styles that characterize QAnon’s messages,” company director Claude Alain Roten told AFP in an interview at his home in western Switzerland.
The conspiracy movement is based on messages from “Q Clearance Patriot,” who claims to be a United States intelligence official leaking classified information.
So-called Q-drops started popping up on the 4chan fringe message board in October 2017 and then moved to 8kun, promoting a vast conspiracy theory that claims President Donald Trump is waging a secret war against a global liberal cult. of Satan-worshiping pedophiles.
There has been speculation about the identity of Q and whether one person is actually behind thousands of these Q drops, but Roten said it was now clear that “two people are behind them.”
“TWO STYLES”
The 60-year-old asked AFP not to disclose the location of the house, which serves as a meeting place for the dozen or so employees currently working from home, out of concern over the reaction to the company’s analysis.
The company performs the so-called sequential stylometric analysis, which statistically analyzes the sequences of characters, comparing the frequency of single letters, pairs of letters or triplets to determine the author or authors of a text.
They use the technique to uncover academic plagiarism, ghostwriters, or, for example, to determine whether parts of a will or contract may have been tampered with.
But Roten, who spent three years in the United States, said he had become increasingly concerned about QAnon’s “population manipulation” there, and had decided to apply his software on the move without getting paid.
A biologist by training, Roten switched fields after realizing that the same principles used to identify genetic codes could help detect the unique characteristics of a person’s writing style.
“I feel like I’m still in the same profession,” he said.
READ: What is QAnon and how are online platforms performing?
“It seems convincing”
His colleague, a lanky 63-year-old with gray hair and a cloth mask who asked to be identified only as Rene, displayed the software on a laptop placed on Roten’s dining room table.
After “cleaning” 4,950 Q-drops of irrelevant content like web links and greetings, it feeds them into the software.
A colored scatter plot appears on the screen, showing two clearly differentiated collections of points.
He said that the graphic showed a clear difference in style between the first Q messages that appeared on 4chan, from October 28 to December 1, 2017, and subsequent messages.
“The signal difference is strong enough to leave very little doubt about this author’s exchange,” OrphAnalytics said in a report published last month.
Florian Cafiero, a renowned stylometric researcher at the French National Center for Scientific Research, said OrphAnalytics’ work on QAnon “looks compelling.”
Stylometry has been around for more than a century, but the advent of computers has dramatically increased the ability to analyze large amounts of data.
OrphAnalytics has made various headlines since its founding in 2014, having put its software to sometimes surprising use.
He helped identify the possible author behind Elena Ferrante’s beloved pseudonym, comparing her writing with samples from two Italian authors suspected of being behind her books, discovering, Roten said, that “Domenico Starnone writes in a style that is indistinguishable from Elena Ferrante “. .
So-called Q-drops started popping up on the 4chan fringe message board in October 2017 claiming that President Donald Trump is waging a secret war against a global liberal cult of Satan-worshiping pedophiles AFP / Fabrice COFFRINI
“DARK SIDE”?
And he has reportedly been hired as an expert witness in criminal cases, including the 1986 unsolved murder of four-year-old Gregory Villemin in France.
Roten declined to say whether his company was working on that case, or to comment on any of the few court cases in which it has been asked to intervene, saying those comments could damage a case.
He said that the company’s approach of focusing exclusively on statistical analysis and eliminating all the context and hypotheses that are generally used to enrich text analysis, helped prevent preconceptions from coloring the result.
“It’s hard to imagine anything more neutral than this,” he said.
Cafiero agreed that the novel adaptation of the technique to the judicial process could help “avoid making mistakes.”
But he expressed concern about the “risks” associated with scaling up the application of increasingly powerful technology, such as potentially helping to identify whistleblowers.
“With any technology, there is light and there is a dark side,” Roten acknowledged, emphasizing that his company had strict ethical guidelines to “prevent our stylometric sequencing approach from being used to serve the dark side.”
As for QAnon’s investigation, he said he felt an obligation to help illuminate who was behind the curtain.
“We are responsible people. If we can act, we act.”
