Computational modeling of face-to-face social interaction using nonverbal behavioral cues

The computational modeling of face-to-face interactions using nonverbal behavioral cues is an emerging and relevant problem in social computing. In the thesis, we have investigated individual social constructs in small groups such as dominance and status (two facets of the so-called vertical dimension of social relations). We have also investigated group social constructs such as conversational context - cooperative vs competitive and brainstorming vs decision making. Our automatic group conversational discovery methods could discover leadership styles that resemble prototypical leadership styles - autocratic, participative, and free-rein - proposed in social psychology.