Attention Networks for Modeling Behaviors in Addiction Counseling

In psychotherapy interactions there are several desirable and undesirable behaviors that give insight into the efficacy of the counselor and the progress of the client. It is important to be able to identify when these target behaviors occur and what aspects of the interaction signal their occurrence. Manual observation and annotation of these behaviors is costly and time intensive. In this paper, we use long short term memory networks equipped with an attention mechanism to process transcripts of addiction counseling sessions and predict prominent counselor and client behaviors. We demonstrate that this approach gives competitive performance while also providing additional interpretability.