Modeling Linguistic (A)Synchrony: A Case Study of Therapist-Client Interaction

Interpersonal synchrony is the alignment of responses between social interactants, and is linked to positive outcomes including cooperative behavior, affiliation, and compassion in different social contexts. Language is noted as a key aspect of interpersonal synchrony, but different strands of existing work on linguistic (a)synchrony tends to be methodologically polarized. We introduce a more complementary approach to model linguistic (a)synchrony that is applicable across different interactional contexts, using psychotherapy talk as a case study. We define linguistic synchrony as similarity between linguistic choices that reflect therapists and clients' socio-psychological stances. Our approach involves (i) computing linguistic variables per session, (ii) k-means cluster analysis to derive a global synchrony measure per dyad, and (iii) qualitative analysis of sample extracts from each dyad. This is demonstrated on sample dyads from psychoanalysis, cognitive-behavioral, and humanistic therapy. The resulting synchrony measures reflect the general philosophy of these therapy types, while further qualitative analyses reveal how (a)synchrony is contextually co-constructed. Our approach provides a systematic and replicable tool for research and self-reflection in psychotherapy and other types of purposive dialogic interaction, on more representative and limited datasets alike.