Predicting the dominant clique in meetings through fusion of nonverbal cues

ABSTRACT

This paper addresses the problem of automatically predicting the dominant clique (i.e., the set of K-dominant people) in face-to-face small group meetings recorded by multiple audio and video sensors. For this goal, we present a framework that integrates automatically extracted nonverbal cues and dominance prediction models. Easily computable audio and visual activity cues are automatically extracted from cameras and microphones. Such nonverbal cues, correlated to human display and perception of dominance, are well documented in the social psychology literature. The effectiveness of the cues were systematically investigated as single cues as well as in unimodal and multimodal combinations using unsupervised and supervised learning approaches for dominant clique estimation. Our framework was evaluated on a five-hour public corpus of teamwork meetings with third-party manual annotation of perceived dominance. Our best approaches can exactly predict the dominant clique with 80.8% accuracy in four-person meetings in which multiple human annotators agree on their judgments of perceived dominance.

REFERENCES

• 1: J. Carletta et al. "The AMI meeting corpus: A pre-announcement," Proc. MLMI Workshop, Edinburgh, UK, Jul. 2005
• 2: N. E. Dunbar et al. "Perceptions of power and interactional dominance in interpersonal relationships," Journal of Social and Personal Relationships, 22(2):207--233, 2005.
• 3: Hayley Hung , Dinesh Jayagopi , Chuohao Yeo , Gerald Friedland , Sileye Ba , Jean-Marc Odobez , Kannan Ramchandran , Nikki Mirghafori , Daniel Gatica-Perez, Using audio and video features to classify the most dominant person in a group meeting, Proceedings of the 15th international conference on Multimedia, September 25-29, 2007, Augsburg, Germany [doi>10.1145/1291233.1291423]
• 4: Kazuhiro Otsuka , Junji Yamato , Yoshinao Takemae , Hiroshi Murase, Quantifying interpersonal influence in face-to-face conversations based on visual attention patterns, CHI '06 extended abstracts on Human factors in computing systems, April 22-27, 2006, Montréal, Québec, Canada [doi>10.1145/1125451.1125672]
• 5: R. J. Rienks and D. Heylen. "Automatic dominance detection in meetings using easily detectable features," Proc. MLMI Workshop, Edinburgh, UK, Jul. 2005
• 6: M. Schmid Mast. "Dominance as expressed and inferred through speaking time: A meta-analysis," Human Communication Research, 28(3):420--450, Jul. 2002.
• 7: L. Smith-Lovin and C. Brody. "Interruptions in Group Discussions: The Effects of Gender and Group Composition, American Sociological Review. 54(3):424--435, Jun. 1989.
• 8: H. Wang et al. "Survey of compressed-domain features used in audio-visual indexing and analysis," Journal of Visual Comm. and Image Representation, 14(2):150--183, 2003.

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.1 Content Analysis and Indexing

General Terms:
Human Factors

Keywords:
dominance modeling, dominant clique, meetings