The New York Times plans to find a way around the worldwide media demon known as comment moderation by enlisting the aid of a Google artificial intelligence.
According to Recode, the publication currently activates comments on a mere 10% of its articles. With this new system – called Moderator – however, it hopes to up this figure to at least 80%.
The site says the software automatically approves a portion of comments, while helping human moderators to trawl through thousands of others.
Moderator is powered by an AI called Perspective, created by Google’s Jigsaw incubator firm, and will aid a team of 14 staff at the New York Times’ moderation section.
“It's become too easy for trolls to dominate conversations online,” says Jigsaw CEO Jared Cohen, speaking to Recode. “People are either leaving the conversation entirely or comments sections are being shut down. The power of machine learning offers us an opportunity to tip the scales and reverse this trend.”
The software won’t be given reign over the site, however. It’s part of a sort of test run, with a human responsible for more complex decisions.
Interestingly, the publication notes that comments sections are about more than just conversations. “We do already write stories based on a lot of user-generated comment across the site,” adds its community editor, Bassey Etim, also speaking to Recode.