2 results
25 - Analysis of Small Groups
- from Part IV - Applications of Social Signal Processing
-
- By Daniel Gatica-Perez, Idiap Research Institute and EPFL, Oya Aran, Idiap Research Institute, Dinesh Jayagopi, IIIT Bangalore
- Edited by Judee K. Burgoon, University of Arizona, Nadia Magnenat-Thalmann, Université de Genève, Maja Pantic, Imperial College London, Alessandro Vinciarelli, University of Glasgow
-
- Book:
- Social Signal Processing
- Published online:
- 13 July 2017
- Print publication:
- 08 May 2017, pp 349-367
-
- Chapter
- Export citation
-
Summary
Introduction
Teams are key components of organizations and, although complexity and scale are typical features of large institutions worldwide, much of the work is still implemented by small groups. The small-group meeting, where people discuss around the table, is pervasive and quintessential of collaborative work. For many years now, this setting has been studied in computing with the goal of developing methods that automatically analyze the interaction using both the spoken words and the nonverbal channels as information sources. The current literature offers the possibility of inferring key aspects of the interaction, ranging from personal traits to hierarchies and other relational constructs, which in turn can be used for a number of applications. Overall, this domain is rapidly evolving and studied in multiple subdisciplines in computing and engineering as well as the cognitive sciences.
We present a concise review of recent literature on computational analysis of face-toface small-group interaction. Our goal is to provide the reader with a quick pointer to work on analysis of conversational dynamics, verticality in groups, personality of group members, and characterization of groups as a whole, with a focus on nonverbal behavior as information source. The value of the nonverbal channel (including voice, face, and body) to infer high-level information about individuals has been documented at length in psychology and communication (Knapp & Hall, 2009) and is one of the main themes of this volume.
In the chapter, we include pointers to 100 publications appearing in a variety of venues between 2009 and 2013 (discussions about earlier work can be found e.g. in Gatica-Perez, 2009.) After a description of our Methodology (see section on Methodology) and a basic quantitative analysis of this body of literature (see section on the Analysis of Main Trends), we select a few works, due to the limited space, in each of the four aforementioned trends to illustrate the kind of research questions, computational approaches, and current performance available in the literature (see sections on Conversational Dynamics, Verticality, Personality, and Group Characterization). Taken together, the existing research on small-group analysis is diverse in terms of goals and studied scenarios, relies on state-of-the-art techniques for behavioral feature extraction to characterize group members from audio, visual, and other sensor sources, and is still largely using standard machine learning techniques as tools for computational inference of interaction-related variables of interest.
9 - Multimodal analysis of small-group conversational dynamics
-
- By Daniel Gatica-Perez, Idiap Research Institute, Martigny, Switzerland, Rieks op den Akker, University of Twente, the Netherlands, Dirk Heylen, University of Twente, the Netherlands
- Edited by Steve Renals, University of Edinburgh, Hervé Bourlard, Jean Carletta, University of Edinburgh, Andrei Popescu-Belis
-
- Book:
- Multimodal Signal Processing
- Published online:
- 05 July 2012
- Print publication:
- 07 June 2012, pp 155-169
-
- Chapter
- Export citation
-
Summary
Introduction
The analysis of conversational dynamics in small groups, like the one illustrated in Figure 9.1, is a fundamental area in social psychology and nonverbal communication (Goodwin, 1981, Clark and Carlson, 1982). Conversational patterns exist at multiple time scales, ranging from knowing how and when to address or interrupt somebody, how to gain or hold the floor of a conversation, and how to make transitions in discussions. Most of these mechanisms are multimodal, involving multiple verbal and nonverbal cues for their display and interpretation (Knapp and Hall, 2006), and have an important effect on how people are socially perceived, e.g., whether they are dominant, competent, or extraverted (Knapp and Hall, 2006, Pentland, 2008).
This chapter introduces some of the basic problems related to the automatic understanding of conversational group dynamics. Using low-level cues produced by audio, visual, and audio-visual perceptual processing components like the ones discussed in previous chapters, here we present techniques that aim at answering questions like: Who are the people being addressed or looked at? Are the involved people attentive? What conversational state is a group conversation currently in? Is a particular person likely perceived as dominant based on how they interact? As shown later in the book, obtaining answers for these questions is very useful to infer, through further analysis, even higher-level aspects of a group conversation and its participants.
The chapter is organized as follows. Section 9.2 provides the basic definitions of three conversational phenomena discussed in this chapter: attention, turn-taking, and addressing.