Proceedings of the Annual Meeting of the Cognitive Science Society

People move in characteristic ways during conversation andthese movements correlate with their level of particpation.For example, speakers normally gesture significantly morethan listeners. These visible, overt movements are normallyanalysed using full body video or motion capture. Here weexplore the potential of a ’minimal’ approach to sensing theseparticipatory movements in part of the natural environmentof everyday interactions; chair seat covers. Using custombuilt fabric sensors we test whether we can detect people’sinvolvement in a conversation using only pressure changeson the seats they are sitting in. We show that even fromthis impoverished data we can distinguish between talking,backchanneling and laughter; each state is associated withdistinctive patterns of pressure change across the surfaceof the chair. We speculate on the possible applications ofthis new, unintrusive form of social sensing for architecture,performance and augmented human interaction.