Antisocial Behavior in Online Discussion Communities

Justin Cheng, Cristian Danescu-Niculescu-Mizil, Jure Leskovec

Proceedings of ICWSM 2015.

Honorable Mention


PDF



Talk Slides (prepared by Justin Cheng)



Related Papers:

                                   Anyone can Become a Troll

                                   How Community Feedback Shapes User Behavior



Media coverage:

                                   BBC: What is the best way to stop internet trolls?

                                   The Daily Dot: Can this algorithm save comment sections from the trolls?

                                   Washington Post: Scientists have figured out how to tell when someone is an online troll

                                   The Guardian: Algorithm 'identifies future trolls from just five posts'

                                   Wired: 'Troll hunting' algorithm could make web a better place

                                   The Economist: Proactive policing

                                   Time Magazine: Science Says You Should Ignore Internet Trolls

                                   Popular Science: Researchers Develop a Troll-Hunting Algorithm

                                   CBC’s Spark: Teaching computers to recognize jerks





ABSTRACT:

                                   

User contributions in the form of posts, comments, and votes are essential to the success of online communities.  However, allowing user participation also invites undesirable behavior such as trolling.  In this paper, we characterize antisocial behavior in three large online discussion communities by analyzing users who were banned from these communities.  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. 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 the community also becomes increasingly less tolerant of their behavior.  Further, we discover that antisocial behavior is exacerbated when community feedback is overly harsh. Our analysis also reveals distinct groups of users with different levels of antisocial behavior that can change over time.  Finally, we use these insights to predict whether a user is likely to develop antisocial behavior early in their community life, a task of high practical importance to community maintainers.




BibTeX ENTRY:

                                   

@InProceedings{Chang+al:15d,

  author={Justin Cheng and Cristian Danescu-Niculescu-Mizil and Jure Leskovec},

  title={Antisocial Behavior in Online Discussion Communities},

  booktitle={Proceedings of ICWSM},

  year={2015}

}