Analyzing the language of therapist empathy in Motivational Interview based psychotherapy. In: Signal & information processing association annual summit and conference (APSIPA ASC

Empathy is an important aspect of social communication, espe-cially in medical and psychotherapy applications. Measures of empathy can offer insights into the quality of therapy. We use an N-gram language model based maximum likelihood strat-egy to classify empathic versus non-empathic utterances and report the precision and recall of classification for various pa-rameters. High recall is obtained with unigram while bigram features achieved the highest F1-score. Based on the utterance level models, a group of lexical features are extracted at the ther-apy session level. The effectiveness of these features in mod-eling session level annotator perceptions of empathy is evalu-ated through correlation with expert-coded session level empa-thy scores. Our combined feature set achieved a correlation of 0.558 between predicted and expert-coded empathy scores. Re-sults also suggest that the longer term empathy perception pro-cess may be more related to isolated empathic salient events