Understanding and Predicting Empathic Behavior in Counseling Therapy

Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, pages 1426–1435 Vancouver, Canada, July 30 - August 4, 2017. c⃝2017 Association for Computational Linguistics https://doi.org/10.18653/v1/P17-1131 Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, pages 1426–1435 Vancouver, Canada, July 30 - August 4, 2017. c⃝2017 Association for Computational Linguistics https://doi.org/10.18653/v1/P17-1131 Understanding and Predicting Empathic Behavior in Counseling Therapy Ver´onica P´erez-Rosas1, Rada Mihalcea1, Kenneth Resnicow2 Satinder Singh1 and Lawrence An3 1Computer Science and Engineering, 2School of Public Health 3Center for Health Communications Research University of Michigan {vrncapr,mihalcea,kresnic,baveja,lcan}@umich.edu Abstract Counselor empathy is associated with bet- ter outcomes in psychology and behav- ioral counseling. In this paper, we ex- plore several aspects pertaining to coun- seling interaction dynamics and their re- lation to counselor empathy during mo- tivational interviewing encounters. Par- ticularly, we analyze aspects such as par- ticipants’ engagement, participants’ verbal and nonverbal accommodation, as well as topics being discussed during the conver- sation, with the final goal of identifying linguistic and acoustic markers of coun- selor empathy. We also show how we can use these findings alongside other raw lin- guistic and acoustic features to build ac- curate counselor empathy classifiers with accuracies of up to 80%. 1 Introduction Behavioral counseling is an important tool to ad- dress public health issues such as mental health, substance abuse, and nutrition problems among others. This has motivated increased interest in the study of mechanisms associated with success- ful interventions. Among them, counselor empa- thy has been identified as a key intervention com- ponent that relates to positive therapy outcomes. Displaying empathic behavior helps counselors to build rapport with their clients. Empathy levels experienced during counseling have a significant effect on treatment outcomes, as clients who per- ceive their counselor as empathic are more likely to improve than the ones who do not (Moyers and Miller, 2013). In this paper, we apply quantitative approaches to understand the dynamics of the counseling in- teractions and their relation to counselor empa- thy. We focus our analysis on counseling con- ducted using Motivational Interviewing (MI), a well-established evidence-based counseling style, where counselor empathy is defined as the active interest and effort to understand the client’s per- spective (Miller and Rollnick, 2013). We address four main research questions. First, are there differences in how the counselor and the client engage during empathic conversations? We explore this question by conducting turn-by-turn word frequency analyses of participant’s interac- tions across the counseling conversations. Second, are there differences in verbal and vocal mimicry patterns occurring during high and low empathy interactions? We address this question by measur- ing the degree of language matching, verbal and nonverbal coordination, and power dynamics ex- pressed during the interaction. Third, are there content differences in counselor discourse during high and low empathy interactions? We answer this question by applying topic modeling to iden- tify the topics that are more salient in high and low empathy interventions (or in both). Finally, fourth, can we build accurate classifiers of coun- selor …

Content truncated to 500 words