Multimodal Behavioral Characterization of Dyadic Alliance in Support Groups

Support groups allow individuals with similar challenges to come together, share their experiences, and receive support. The psychological benefits of participating in a support group heavily rely on peer support and group connectedness. Hence, a high degree of dyadic alliance between group participants is crucial to successful support groups. This paper investigates the verbal and nonverbal behaviors associated with peer-to-peer dyadic alliance in support groups. Multimodal behavioral data were collected from 96 participants of 18 support group sessions, moderated by a virtual embodied conversational agent (ECA). Statistical analysis revealed that select facial expressions and head gestures are significant predictors of dyadic alliance. We develop a multimodal machine learning model to quantify alliance between dyads (i.e., participant pairs in sessions), achieving a weighted F1 score of 0.752 and a balanced accuracy of 0.590 under session-independent cross-validation. This work represents, to the best of our knowledge, the first computational study on dyadic alliance and its behavioral markers. The findings offer potential opportunities for improving support-group facilitator training and automated facilitation systems, with the aim of expanding access to care.