Google builds AI to identify potential trolls

[oldmanwinters]

Seems like something out of the movie Minority Report:
http://finance.yahoo.com/news/how-go...123048658.html

The company’s latest effort is called the Perspective API. Available Thursday, Feb. 23, Perspective is the result of Jigsaw’s Conversation AI project and uses Google’s machine learning technologies to provide online publishers with a tool that can automatically rank comments in their forums and comments sections based on the likelihood that they will cause someone to leave a conversation. Jigsaw refers to this as a “toxicity” ranking.

“At its core, Perspective is a tool that simply takes a comment and returns back this score from 0 to 100 based on how similar it is to things that other people have said that are toxic,” explained product manager CJ Adams.

Jigsaw doesn’t become the arbiter of what commenters can and can’t say in a publisher’s comment section, though. Perspective is only a tool that publishers use as they see fit. For example, they can give their readers the ability to filter comments based on their toxicity level, so they’ll only see non-toxic posts. Or the publisher could provide a kind of feedback mechanism that tells you if your comments are toxic.

The tool won’t stop you from submitting toxic comments, but it will provide you with the nudge to rethink what you’re writing.