Dyadic Behavior Informatics for Psychotherapy Process and Outcome

Dyadic Behavior Informatics for Psychotherapy Process and Outcome

The goal of this project is to develop computational representations that can model fine-grained dyadic coordination between clients and therapists and new algorithms that can model multi-level dynamics within and between sessions. We introduce a new computational framework, named Dyadic Behavior Informatics, specifically designed to develop and evaluate nonverbal behavioral indicators that predict process and outcome measures of psychotherapy. The unique aspect of our proposed work, motivated by the recent findings on working alliance, is the explicit modeling of both therapist and client behaviors during their dyadic interactions. This research will pave the way to a better understanding of the dyadic behavior dynamics in psychotherapy, build the computational foundations to predict process and outcomes, and more broadly inform behavioral science.