Motivational interviewing is a goal-oriented psychotherapy, employed in cases such as addiction, that aims to help clients explore and resolve their ambivalence about their problem. In motivational interviewing, it is desirable for the counselor to communicate empathy towards the client to promote better therapy outcomes. In this paper, we propose a deep neural network (DNN) system for predicting counselors' session level empathy ratings from transcripts of the interactions. First, we train a recurrent neural network mapping the text of each speaker turn to a set of task-specific behavioral acts that represent local dynamics of the client-counselor interaction. Subsequently, this network is used to initialize lower layers of a deep network predicting session level counselor empathy rating. We show that this method outperforms training the DNN end-to-end in a single stage and also outperforms a baseline neural network model that attempts to predict empathy ratings directly from text without modeling turn level behavioral dynamics. Index Terms: behavioral signal processing, recurrent neural networks, word embedding, motivational interviews 1 Note: we italicize empathy to distinguish this specific operational definition from colloquial definitions.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.