A Nonverbal Behavior Approach to Identify Emergent Leaders in Small Groups

Abstract

Abstract-Identifying emergent leaders in organizations is a key issue in organizational behavioral research, and a new problem in social computing. This paper presents an analysis on how an emergent leader is perceived in newly formed, small groups, and then tackles the task of automatically inferring emergent leaders, using a variety of communicative nonverbal cues extracted from audio and video channels. The inference task uses rule-based and collective classification approaches with the combination of acoustic and visual features extracted from a new small group corpus specifically collected to analyze the emergent leadership phenomenon. Our results show that the emergent leader is perceived by his/her peers as an active and dominant person; that visual information augments acoustic information; and that adding relational information to the nonverbal cues improves the inference of each participant's leadership rankings in the group.

Emergent leaders through looking and speaking: from audio-visual data to multimodal recognition

“…As we can observe the amount of interruptions (SPI) are significantly correlated with PLead, PDom and RDom. Similarly, significant correlations between interruptions and concepts of dominance and leadership have been reported in (Hung et al, 2008;Jayagopi et al, 2009;Sanchez-Cortes et al, 2011b).…”

“…In (Sanchez-Cortes et al, 2010) we presented our first experiments on a subset of the ELEA corpus. Later on, the full ELEA corpus and a comprehensive study on emergent leadership estimation using communicative nonverbal features was presented in (Sanchez-Cortes et al, 2011b), where performance of audio and visual activity features were described separately as well as aggregated through feature fusion. The details of our experience collecting the ELEA corpus and a brief analysis between emergent leadership and its possible association with personality was presented at the MMC Workshop in 2011 (Sanchez-Cortes et al, 2011a).…”

“…The ELEA AVS corpus is a subset of selected recordings from the ELEA corpus (Sanchez-Cortes et al, 2011b). This subset corresponds to recordings using a fully portable setup, with no video frame dropping.…”

“…We used the survival experts' ranking list to code some variables related to performance and influence, the description can be found in (Sanchez-Cortes et al, 2011b).…”

“…Considering that nonverbal behavior extracted from audio and visual single channel can be used to identify the emergent leaders (Sanchez-Cortes et al, 2011b), multimodal features extracted from synchronized audio and video might provide a better understanding of the nonverbal behavior of the emergent leader. Figure 9 shows performance using the unsupervised method and the multimodal features, where the best performance to identify the leader is using either BLWS or CAWS with up to 63.6%.…”