Predicting Remote Versus Collocated Group Interactions
using Nonverbal Cues
Dairazalia Sanchez-Cortes, Dinesh Babu Jayagopi, and Daniel Gatica-Perez
accepted for publication in Workshop on Multimodal Sensor-Based Systems and Mobile Phones for Social Computing - International Conference on Multimodal Interfaces (ICMI-MLMI),Cambridge 2009. (pdf)
This paper addresses two problems: Firstly, the problem of
classifying remote and collocated small-group working meet
ings, and secondly, the problem of identifying the remote
participant, using in both cases nonverbal behavioral cues.
Such classifiers can be used to improve the design of remote
collaboration technologies to make remote interactions as ef
fective as possible to collocated interactions. We hypothesize
that the difference in the dynamics between collocated and
remote meetings is significant and measurable using speech
activity based nonverbal cues. Our results on a publicly
available dataset - the Augmented Multi-Party Interaction
with Distance Access (AMIDA) corpus - show that such an
approach is promising, although more controlled settings
and more data are needed to explore the addressed prob
lems further.
