This work addresses the problem of mining group conversational and gaze patterns in the Emergent Leaderhip(ELEA) corpus. We study 18 groups of four participants. Our group cues describe group members' aggregated nonverbal behaviour. Then, we use topic models to discover typical patterns of group behavior based on the co-occurrence of several of these cues. Finally, we relate our group cues and topics to concepts well studied in small group research: group composition, group perception and group performance. Funded by : Project NISHA
This work addresses the novel problem of characterizing conversational group dynamics. It is well documented in social psychology that depending on the objectives a group, the dynamics are different. For example, a competitive meeting has a different objective from that of a colloborative meeting. We study methods to characterize group dynamics based on the joint description of a group members' aggregated acoustical nonverbal behaviour to classify meeting datasets.
Dominance - a behavioral expression of power - is a fundamental mechanism of social interaction, expressed and perceived in conversations through spoken words and audio-visual nonverbal cues. Status- an ascribed or achieved quality implying respect or privilege, [but] does not necessarily include the ability to control others or their resources. The automatic modeling of dominance or status patterns from sensor data represents a relevant problem in social computing.