NISHA: NTT - Idiap Social beHavior Analysis Initiative
Introduction
Teamwork is pervasive in organizations and societies, and so are the possibilities to sense group interaction and build systems that enable self and group awareness. Group members in interactions backchannel and gaze at each other, smile and nod as responses to others. These dyadic nonverbal cues are revealing of key aspects of the relationships existing among team members.
In this project, we address the problem of automatic inference of relational social constructs in group conversations using nonverbal behavior. We focus on dyadic social phenomena emerging in small groups - a novel area of research in social computing.
Using probabilistic methods, NISHA aims to discover these dyadic nonverbal patterns, analyze their properties, and use this knowledge to characterize relationships among the members of teams. We work with audio-visual data from groups solving tasks together, recorded using portable sensors [microcone].
Keywords: automatic behavior analysis, relational cues, machine learning, NTT, Idiap.