Towards automatic detection of antisocial behavior from texts

The automatic analysis of emotional content of text has become pervasive and has been applied in many fields of research. The work reported in this paper is in particular interested in modeling antisocial behavior and the emotional states that define it. We introduce the antisocial behavior detection (ASBD) model for portraying the emotions pertaining to antisocial behavior. In addition to describing negative affective states, our model uses the concepts of action tendencies and evidences in order to predict possible acts of antisocial behavior based on input texts. We outline a design for an antisocial behavior detection system based on the ASBD model.