Quoting from the Cornell & Stanford paper I linked above:
While most users tend to be civil, others may engage in antisocial behavior, negatively affecting other users and harming the community. Such undesired behavior, which includes trolling, flaming, bullying, and harassment, is exacerbated by the fact that people tend to be less inhibited in their online interactions (Suler 2004).
[We are addressing] several questions about antisocial behavior: First, are there users that only become antisocial later in their community life, or is deviant behavior innate? Second, does a community’s reaction to users’ anti- social behavior help them improve, or does it instead cause them to become more antisocial? Last, can antisocial users be effectively identified early on?
I'm using this paper as a lens to view the posts from users - particularly the researchers' discussion of the work they did to predict FBUs (Future Banned Users).
In fact, we only need to observe 5 to 10 user’s posts before a classifier is able to make a reliable prediction. Further, cross- domain classification performance remains high, suggesting that the features indicative of antisocial behavior that we discover are not community-specific.