Researchers Developing An Algorithm That Can Detect Internet Trolls

An anonymous reader writes Researchers at Cornell University claim to be able to identify a forum or comment-thread troll within the first ten posts after the user joins with more than 80% accuracy, leading the way to the possibility of methods to automatically ban persistently anti-social posters. The study observed 10,000 new users at cnn.com, breitbart.com and ign.com, and characterizes an FBU (Future Banned User) as entering a new community with below-average literacy or communications skill, and that the low standard is likely to drop shortly before a permanent ban. It also observes that higher rates of community intolerance are likely to foster the anti-social behavior and speed the ban.

Comments

Re:This, if true, will utterly destroy

[circletimessquare]

The local CBS news affiliate in New York uses disqus.

Go here

http://newyork.cbslocal.com/

Click any story with a whiff of crime, on any day.

Guaranteed racist hate.

It's like a hang out spot for old feeble bigots.

I don't understand why a serious media company like CBS News wants their brand to be associated with constant racist ignorance, but it's been this way for years.

You could imagine that being an old media company it has brought online and attracted the equally old racists.

But still: why would CBS corporate want that to persist, for years, regardless of the reason why their forum is a hang out place for intolerant morons?

Even if CBS New York is run by racists, even such a person could see how being linked to such constant hate would hurt their bottom line, and that the almighty dollar would demand the racism be scrubbed from their website. But no, it's a magnet and hang out for racist hate.

Bizarre.