Announcement

Collapse
No announcement yet.

Trolls

Collapse
X
 
  • Filter
  • Time
  • Show
Clear All
new posts

  • Trolls

    http://www.theguardian.com/technolog...ust-five-posts

    It is possible to tell comment trolls apart from other users simply from looking at the way they write, researchers have found.
    Studying the comments on three sites – CNN, Breitbart and IGN – over an 18 month period, the researchers at Cornell and Stanford universities found that users who went on to be banned wrote differently to other users in the same comment thread, using fewer words indicative of positive emotion.

    Future banned users also tended to write comments that were more difficult to read than typical users, the researchers found.
    “We find that such users tend to concentrate their efforts in a small number of threads, are more likely to post irrelevantly, and are more successful at garnering responses from other users,” the researchers add, in a pre-publication paper titled Antisocial Behavior in Online Discussion Communities.

    “Studying the evolution of these users from the moment they join a community up to when they get banned, we find that not only do they write worse than other users over time, but they also become increasingly less tolerated by the community.

    The researchers also discovered that antisocial behaviour was exacerbated when moderation appears to be overly harsh.

    The researchers studied more than 35m posts sent from almost 2 million users on the three websites under investigation, and found nearly 50,000 individual users who had been banned over the 18 month period. They also examined the number of individual comments that had been deleted or reported to the site’s moderators, with all the data provided to the researchers by Disqus, the commenting platform used by all three sites.

    They focused their investigation on the 50,000 users banned over the period under examination, and attempted to find tell-tale signs in their prior posts that acted as an indicator for their later behaviour.

    They discovered that users who would end up being banned from the site often wrote noticeably different to the main bulk of commenters. “Users can stay on-topic or veer off-topic; prior work has also shown that users tend to adopt linguistic conventions or jargon in a community … and that they also unconsciously mimic the choices of function-word classes they are communicating with.” Sure enough, they found that “text similarity” of banned users was significantly lower than that of non-banned users.

    Additionally, the posts of banned users had similar word counts to those of non-banned, but when tested against a standard readability index were revealed to be significantly harder to read.

    On top of the information found in the actual posts, the authors also found that users who would go on to be banned interacted differently with the community at large. “For instance, [future banned users] tended to spend more time in individual threads than [users who weren’t banned],” they write.

    With all the information together, they created a prediction model which can guess with 80% accuracy whether or not that user will go on to be banned from just their first five posts. Looking at the first 10 raises the accuracy of the model by a further two percentage points, which raises the possibility of automatically highlighting potentially problematic users to moderators so that antisocial behaviour can be dealt with more quickly.

    But the authors warn that overzealous moderation can have its own downside: “Taking extreme action against small infractions can exacerbate antisocial behaviour (e.g. unfairness can cause users to write worse) … Whereas trading off overall performance for higher precision and have a human moderator approve any bans is one way to avoid incorrectly blocking innocent users, a better response may instead involve giving antisocial users a chance to redeem themselves.”

  • #2
    I don't understand this article at all.

    Comment


    • #3
      Originally posted by Missnaughty View Post
      I don't understand this article at all.
      Basically, it says that researchers have identified similarities in the way trolls post on message boards. They have characteristics in common that are different from the way ordinary users post. The researchers say that these similarities can be used to create software that would scan posts and flag potential trolls. They have tested this - if they get to analyze the first 5 posts of a new user, they can predict with 80% accuracy whether the person will go on to be banned or not. If they get to analyze the first 10 posts, the accuracy increases a little.

      These are the common features of posts by trolls:

      1. Trolls use fewer words that indicate positive emotion
      2. Trolls don't mimic the culture/wording style of the message board
      3. Posts written by trolls tend to be harder to understand
      4. Trolls tend to post in only a small number of threads

      Does that help?

      I think the algorithm for troll identification might not work so well at LIIEF:

      1. Trolls use fewer words that indicate positive emotion
      yes, that would work!

      2. Trolls don't adopt the lingo/culture of the message board
      That might not work within 5-10 posts, because LIIEF probably represents a very different environment for a lot of new posters (Indonesians getting their first exposure to English message boards; potential expats who don't have experience with Indonesia). It might take them longer to become fluent in "LIIEF-ese."

      3. The posts that trolls write are harder to understand
      Legitimate posters whose native language is not English are more likely to write posts that are hard to understand.

      4. Trolls tend to post in only a small number of threads
      That would work sometimes, but not always; a new poster who is only here to get information about a specific topic might start a thread with a question and only participate in that thread.

      Having said that, I do think the research is valid. I can think of one or two posters who pop up every so often, fit that profile nicely and, in my mind, are posting trollishly.
      Last edited by Puspawarna; 20-04-15, 17:43. Reason: typos, dammit!

      Comment


      • #4
        Occasionally I enjoy a troll. They're sometimes able to ignite discussion even though their motive may have been to disrupt or attract attention to themselves. Their virtual beatings are also often quite entertaining.
        [COLOR=#008000][FONT=arial]I tried to wrestle my inner demons once... but they used too many illegal holds.[/FONT][/COLOR]

        Comment


        • #5
          Originally posted by Vanhellsink View Post
          Occasionally I enjoy a troll. They're sometimes able to ignite discussion even though their motive may have been to disrupt or attract attention to themselves. Their virtual beatings are also often quite entertaining.
          agreed .... I enjoy a bit of abuse occasionally .... brings me back to reality, like a buddhist playing rugby
          The answer is 42 .... any questions? .

          Comment


          • #6
            I watched a very informative report on one of the news channels about the Russian troll army as it was called. Whereby governments and corporations actually employ thousands of people to swamp the internet chat rooms, comments areas, Facebook and forums etc. in order to push a certain political agenda or point of view.

            http://www.aljazeera.com/programmes/...093244109.html

            Comment


            • #7
              Originally posted by Puspawarna View Post
              ...I think the algorithm for troll identification might not work so well at LIIEF:

              1. Trolls use fewer words that indicate positive emotion
              yes, that would work!

              2. Trolls don't adopt the lingo/culture of the message board
              That might not work within 5-10 posts, because LIIEF probably represents a very different environment for a lot of new posters (Indonesians getting their first exposure to English message boards; potential expats who don't have experience with Indonesia). It might take them longer to become fluent in "LIIEF-ese."

              3. The posts that trolls write are harder to understand
              Legitimate posters whose native language is not English are more likely to write posts that are hard to understand.

              4. Trolls tend to post in only a small number of threads
              That would work sometimes, but not always; a new poster who is only here to get information about a specific topic might start a thread with a question and only participate in that thread.

              Having said that, I do think the research is valid. I can think of one or two posters who pop up every so often, fit that profile nicely and, in my mind, are posting trollishly.
              What's the acronym "LIIEF" mean in this context?

              Comment


              • #8
                Originally posted by waarmstrong View Post
                What's the acronym "LIIEF" mean in this context?
                Living In Indonesia Expat Forum

                Comment


                • #9
                  Originally posted by Puspawarna View Post
                  Living In Indonesia Expat Forum
                  I suppose in the future the whole English language will be in acronym, especially the younger generation, because as an old fart I wonder what the hell has been written in some SMS I get

                  Comment


                  • #10
                    I may be the only person who writes "LIIEF" although I have seen other people refer to it as LII.

                    Comment


                    • #11
                      Originally posted by Anglian View Post
                      I suppose in the future the whole English language will be in acronym, especially the younger generation, because as an old fart I wonder what the hell has been written in some SMS I get
                      What does SMS stand for?

                      Comment


                      • #12
                        Originally posted by Puspawarna View Post
                        What does SMS stand for?
                        Isnt that a bondage term?
                        Sasa Bule is having a bayi!

                        Comment


                        • #13
                          Originally posted by Puspawarna View Post
                          What does SMS stand for?
                          Funnily enough, I know what it is, but no idea what it stands for, any one?

                          Comment


                          • #14
                            I think it comes from standard messaging service, or something like that, but I'm not sure.

                            Comment


                            • #15
                              Originally posted by Puspawarna View Post
                              I think it comes from standard messaging service, or something like that, but I'm not sure.
                              Short Message Service

                              Comment

                              Working...
                              X