Abstract

User satisfaction is an important aspect of the user expe- rience while interacting with objects, systems or people. Tra- ditionally user satisfaction is evaluated a-posteriori via spoken or written questionnaires or interviews. In automatic behav- ioral analysis we aim at measuring the user emotional states and its descriptions as they unfold during the interaction. In our approach, user satisfaction is modeled as the final state of a sequence of emotional states and given ternary values positive, negative, neutral. In this paper, we in- vestigate the discriminating power of turn-taking in predicting user satisfaction in spoken conversations. Turn-taking is used for discourse organization of a conversation by means of ex- plicit phrasing, intonation, and pausing. In this paper, we train different characterization of turn-taking, such as competitive- ness of the speech overlaps. To extract turn-taking features we design a turn segmentation and labeling system that incorpo- rates lexical and acoustic information. Given a human-human spoken dialog, our system automatically infers any of the three values of the state of the user satisfaction. We evaluate the clas- sification system on real-life call-center human-human dialogs. The comparative performance analysis shows that the contribu- tion of the turn-taking features outperforms both prosodic and lexical features.