2019/04/11 by Nasır, Sandeep Nallan Chakravarthula, Nasir, Md +11 · 1 citation
Computer Science · Neuroscience · Psychology · #Action Observation and Synchronization #Computation and Language (cs.CL) #FOS: Computer and information sciences #Language, Metaphor, and Cognition #Natural Language Processing Techniques #Neurobiology of Language and Bilingualism
paper · pdf · doi:10.48550/arxiv.1904.06002
openalex publication_date 2019/04/11 · openalex created_date 2022/07/24 · openalex updated_date 2026/07/28
Linguistic coordination is a well-established phenomenon in spoken\nconversations and often associated with positive social behaviors and outcomes.\nWhile there have been many attempts to measure lexical coordination or\nentrainment in literature, only a few have explored coordination in syntactic\nor semantic space. In this work, we attempt to combine these different aspects\nof coordination into a single measure by leveraging distances in a neural word\nrepresentation space. In particular, we adopt the recently proposed Word\nMover's Distance with word2vec embeddings and extend it to measure the\ndissimilarity in language used in multiple consecutive speaker turns. To\nvalidate our approach, we apply this measure for two case studies in the\nclinical psychology domain. We find that our proposed measure is correlated\nwith the therapist's empathy towards their patient in Motivational Interviewing\nand with affective behaviors in Couples Therapy. In both case studies, our\nproposed metric exhibits higher correlation than previously proposed measures.\nWhen applied to the couples with relationship improvement, we also notice a\nsignificant decrease in the proposed measure over the course of therapy,\nindicating higher linguistic coordination.\n