tailieunhanh - Báo cáo khoa học: "Contrasting Multi-Lingual Prosodic Cues to Predict Verbal Feedback for Rapport"

Verbal feedback is an important information source in establishing interactional rapport. However, predicting verbal feedback across languages is challenging due to languagespecific differences, inter-speaker variation, and the relative sparseness and optionality of verbal feedback. In this paper, we employ an approach combining classifier weighting and SMOTE algorithm oversampling to improve verbal feedback prediction in Arabic, English, and Spanish dyadic conversations. | Contrasting Multi-Lingual Prosodic Cues to Predict Verbal Feedback for Rapport Siwei Wang Department of Psychology University of Chicago Chicago IL 60637 USA siweiw@ Gina-Anne Levow Department of Linguistics University of Washington Seattle Wa 98195 USA levow@ Abstract Verbal feedback is an important information source in establishing interactional rapport. However predicting verbal feedback across languages is challenging due to languagespecific differences inter-speaker variation and the relative sparseness and optionality of verbal feedback. In this paper we employ an approach combining classifier weighting and SMOTE algorithm oversampling to improve verbal feedback prediction in Arabic English and Spanish dyadic conversations. This approach improves the prediction of verbal feedback up to 6-fold while maintaining a high overall accuracy. Analyzing highly weighted features highlights widespread use of pitch with more varied use of intensity and duration. 1 Introduction Culture-specific aspects of speech and nonverbal behavior enable creation and maintenance of a sense of rapport. Rapport is important because it is known to enhance goal-directed interactions and also to promote learning. Previous work has identified cross-cultural differences in a variety of behaviors for example nodding Maynard 1990 facial expression Matsumoto et al. 2005 gaze Watson 1970 cues to vocal back-channel Ward and Tsukuhara 2000 Ward and Al Bayyari 2007 Rivera and Ward 2007 nonverbal back-channel Bertrand et al. 2007 and coverbal gesturing Kendon 2004 . Here we focus on the automatic prediction of listener verbal feedback in dyadic unrehearsed storytelling to elucidate the similarities and differences 614 in three language cultural groups Iraqi Arabic- Mexican Spanish- and American English-speaking cultures. Tickle-Degnen and Rosenthal 1990 identified coordination along with positive emotion and mutual attention as a key element of interactional rapport. In the .