Google launches technology to help publishers find malicious comments on articles

Alphabet Inc’s Google and subsidiary Jigsaw on Thursday launched a new technology to help news organisations and online platforms identify abusive comments on their websites.

The technology, called Perspective, will review comments and score them based on how similar they are to comments people said were “toxic” or likely to make them leave a conversation.

It has been tested on the New York Times and the companies hope to extend it to other news organisations such as The Guardian and The Economist as well as websites.

“News organisations want to encourage engagement and discussion around their content, but find that sorting through millions of comments to find those that are trolling or abusive takes a lot of money, labour, and time.

“As a result, many sites have shut down comments altogether,” Jared Cohen, President of Jigsaw, which is part of Alphabet, wrote in a blog post.

“But they tell us that isn’t the solution they want. We think technology can help.”

Perspective examined hundreds of thousands of comments that had been labelled as offensive by human reviewers to learn how to spot potentially abusive language.

CJ Adams, Jigsaw Product Manager, said the company was open to rolling out the technology to all platforms, including larger ones such as Facebook and Twitter where trolling can be a major headache.

The technology could in the future be expanded to trying to identify personal attacks or off-topic comments too, Cohen said.

Perspective will not decide what to do with comments it finds are potentially abusive; rather publishers will be able to flag them to their moderators or develop tools to help comment understand the impact of what they are writing.

Mr. Cohen said a significant portion of abusive comments came from people who were “just having a bad day”.

The initiative against trolls follows efforts by Google and Facebook to combat fake news stories in France, Germany and the U. S. after they came under fire during the presidential vote when it became clear they had inadvertently fanned false news reports.

The debate surrounding fake news has led to calls from politicians for social networks to be held more liable for the content posted on their platforms.

The Perspective technology is still in its early stages and “far from perfect”, Mr. Cohen said, adding he hoped it could be rolled out for languages other than English too.



Now available on

  Premium Times Android mobile applicationPremium Times iOS mobile applicationPremium Times blackberry mobile applicationPremium Times windows mobile application


All rights reserved. This material and any other material on this platform may not be reproduced, published, broadcast, written or distributed in full or in part, without written permission from PREMIUM TIMES.

  • Watch man

    I think this move would help in muzzling public opinion as criteria for determining abusive language might be subjective.

  • Impulse400


    Bad news for pastor Taiwo and his crew. Popone et al.

  • Otile

    This will be a blow to many Odua commentators. If you purge insults, and raw language many Odua commentators will have nothing to write again. Can you imagine awon omo Odua like tundemash not using the word moron, or julius not calling those he does not know homo? Touts like artful dodger and mofu ola will be speechless without having access to insults. It is going to be interesting.

    • blueeyedkitten

      your constant trolling would soon be over. find another job before it is launched.

      • Otile

        You are speaking from your own experience. Why are you worried?