Modeling Dominance in Group Conversations Using Nonverbal Activity Cues

Abstract

Abstract-Dominance -a behavioral expression of power -is a fundamental mechanism of social interaction, expressed and perceived in conversations through spoken words and audio-visual nonverbal cues. The automatic modeling of dominance patterns from sensor data represents a relevant problem in social computing. In this paper, we present a systematic study on dominance modeling in group meetings from fully automatic nonverbal activity cues, in a multi-camera, multi-microphone setting. We investigate efficient audio and visual activity cues for the characterization of dominant behavior, analyzing single and joint modalities. Unsupervised and supervised approaches for dominance modeling are also investigated. Activity cues and models are objectively evaluated on a set of dominance-related classification tasks, derived from an analysis of the variability of human judgment of perceived dominance in group discussions. Our investigation highlights the power of relatively simple yet efficient approaches and the challenges of audio-visual integration. This constitutes the most detailed study on automatic dominance modeling in meetings to date.

Predicting online lecture ratings based on gesturing and vocal behavior

“…Research efforts targeted a wide spectrum of problems, including conflict detection [28], communication dynamics [7,25], mimicry measurement [10], early detection of developmental and cognitive diseases [37], role recognition [38], prediction of negotiation outcomes [9], videosurveillance [4,5,6,8], etc. Furthermore, several works were dedicated to the automatic prediction of traits likely to be relevant in a teaching context like, in particular, personality [21,23,30] and dominance [13,27,34,35].…”

“…Similar speaking related features were fed to a Dynamic Bayesian Network in [27], together with visual attention features (who looks at whom) in order to predict the most dominant person in a meeting. A similar multimodal approach was proposed in [13].…”

Privacy-sensitive recognition of group conversational context with sociometers

“…Regarding individual behavior modeling, attempts have been made to estimate dominant behavior, certain personality traits, and certain roles that individuals are involved in. Jayagopi et al estimate dominant behavior by computing speaking turns-based features (like speaking time, turns, successful interruptions) along with motion turns and learning supervised models using Support Vector Machines (SVM) on meetings from the AMI (Augmented Multiparty Interaction) corpus [4,23]. Pianesi et al [39,40] estimate personality traits, specifically extraversion (sociable, assertive, playful) versus intraversion (aloof, reserved, shy) using Support Vector Regression and applied to sequences of the MS (Mission Survival) Corpus.…”

More Than Words: Inference of Socially Relevant Information from Nonverbal Vocal Cues in Speech

“…, a G } (G is the total number of speakers in the conversation and the a i are the speaker labels). Even if such an information is relatively basic and it seems to miss the richness of a conversation, still it allows one to capture a wide range of social phenomena such as the groups forming around discussion topics [13], the fronts opposing one another in competitive discussions [12], dominant individuals [8], etc. The rest of this section shows how the same information can be used to infer the roles in several interaction settings.…”