Effect of nonverbal behavioral patterns on the performance of small groups

In this paper, we investigate the links between the interaction among the group members and team performance, as well as the group composition. Towards this goal, we extract nonverbal audio-visual behavioral features from the group interaction and apply a multivariate binary Influence Model to quantify interactions between team members. We compare and contrast the differences between forms of interaction for distinct performance clusters and describe the factors affecting group performance in terms of group members' influences on each other and traits such as dominance. Our results show that different performance clusters have different interaction types and the groups with high and low performance have a structure where the group members are influenced by one or more people, in contrast to one-to-one pairwise influences. The performance of individuals with specific traits, such as leaders and competent people, has a significant correlation with the group performance, with a correlation coefficient of over 0.50.