Identification of emergent leaders in a meeting scenario using multiple kernel learning

Abstract

In this paper, an effective framework for detection of emergent leaders in small group is presented. In this scope, the combination of different types of nonverbal visual features; the visual focus of attention, head activity and body activity based features are utilized. Using them together ensued significant results. For the first time, multiple kernel learning (MKL) was applied for the identification of the most and the least emergent leaders. Taking the advantage of MKL's capability to use different kernels which corresponds to different feature subsets having different notions of similarity, significantly improved results compared to the state of the art methods were obtained. Additionally, high correlations between the majority of the features and the social psychology questionnaires which are designed to estimate the leadership or dominance were demonstrated.

Perceiving Leadership Structures in Teams: Effects of Cognitive Schemas and Perceived Communication

“…Whereas existing evidence implies that individual predispositions affect the way leadership is perceived and rated (e.g., Keller Hansbrough et al, 2015), information processing theories of leadership (Lord, 1985; Lord et al, 1982; Lord & Maher, 1993) propose that individuals have specific expectations and attitudes toward leadership that influence both the interpersonal behavior and the perception of behavior in team collaborations. Through communication behavior, the team members exchange information (Beyan et al, 2016) on relevant knowledge, competence, which should form the basis for decisions on whom to grant influence within the team (Anderson & Kilduff, 2009).…”

An Exploratory Computational Study on the Effect of Emergent Leadership on Social and Task Cohesion

“…Automated detection of emergent leadership is raising interest in the organizational environment as it has been related to the improvement of team productivity and performance [46]. Several datasets were collected to study such an emergent state (e.g., ELEA [43], PAVIS [7]) and used by several studies (e.g., [5,8,39]). Since nonverbal features have been found to be more informative than verbal features for the analysis of social phenomena (e.g., [1,29]) computational studies addressing the automated detection of emergent leadership used nonverbal features (e.g., [6,43]).…”

Adapting Leadership Perceptions Across Tasks: Micro-Origins of Informal Leadership Transitions

“…and build up memory representations about these events" (Malle & Pearce, 2001, p. 278), which leads to the generation and processing of information (Lichtenstein et al, 2007;Lord, 1985;Marion et al, 2016). Social interactions provide social information as they include verbal and nonverbal communication (e.g., eye gaze, head-body orientation, facial expression) between a sender and an observer (Beyan, Capozzi, Becchio, & Murino, 2016). The availability of such social information is crucial, as perceivers make their leadership judgments through a retrospective social-cognitive evaluation process (Lord, Day, Zaccaro, Avolio, & Eagly, 2017).…”