Slashdot Mirror
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.
Of course, I haven't read the article, but I think the summary has applied the word "troll" in a different way than this. I think the researchers are seeking to reduce the racist, homophobic, etc. trash comments frequently posted to YouTube video comments.
As you note here, a sophisticated troll is not easily detectable via AI.
Of course neither I read the article, but if researchers are seeking to reduce the racist, homophobic, etc. trash comments, wouldn't be better to just permit comments only from registered Democrats? So, if someone wants to comment about niggers, faggets, libtards, etc, must be a registered Democrat (that way free speech is guaranteed for all) and niggers, faggets, libtards, etc, can still rule!
Does the algorithm account for the fact that the Troll designation is applied by some specific person who (a) has mod points, (b) strongly disagrees with a given post and (c) is in many cases part of a group who is looking for antagonists to some cause that group really believes in.
Don't worry, either using the algorithm or a moderation system like Slashdot's, free speech is always guaranteed - e.g., with Slashdot's moderation the troll designation is given by the niggers, faggets, libtards, etc, moderators to those commenting about niggers, faggets, libtards, etc; with the algorithm we can do the same, although without the direct human satisfaction of doing the ethically right censorship.