It’s being used to fight ISIS, and now, an app developed by a subsidiary of Google is tackling another kind of vitriol — online trolls.
Jigsaw, an organization that once existed as Google’s think tank, has now taken on a new life of its own and has been tasked with using technology to address a range of geopolitical issues. The latest software to come out of the group is an artificial intelligence tool known as Conversation AI. As Wired reports, “the software is designed to use machine learning to automatically spot the language of abuse and harassment — with, Jigsaw engineers say, an accuracy far better than any keyword filter and far faster than any team of human moderators.
Conversation AI learns and automatically flags problematic language, and assigns it an “attack score” that ranges from 0 to 100. A score of 0 suggests that the language in question is not at all abusive, whereas a score of 100 suggests that it is extremely harmful.
And it looks like it’s working. As Wired notes, “Jigsaw has now trained Conversation AI to spot toxic language with impressive accuracy. Feed a string of text into its Wikipedia harassment-detection engine and it can, with what Google describes as more than 92 percent certainty and a 10-percent false-positive rate, come up with a judgment that matches a human test panel as to whether that line represents an attack.”
Currently, the plan is to test Conversation AI first in the New York Times’ comments section (though perhaps YouTube would be a better place to start), and Wikipedia also plans on making use of the software, though it’s unclear how.
“I want to use the best technology we have at our disposal to begin to take on trolling and other nefarious tactics that give hostile voices disproportionate weight,” Jigsaw founder and president Jared Cohen told Wired, “to do everything we can to level the playing field.”
Eventually, Conversation AI will become open source so that any site can make use of its anti-trolling capabilities to protect its users. So advanced is the technology already that it can “automatically flag insults, scold harassers, or even auto-delete toxic language.”
So look out, internet trolls of the world. It looks like your days of abuse may be numbered.
