Towards Computational Proxemics: Inferring Social Relations from Interpersonal Distances

This paper proposes a study corroborated by preliminary experiments on the inference of social relations based on the analysis of interpersonal distances, measured with onobtrusive computer vision techniques. The experiments have been performed over 13 individuals involved in casual standing conversations and the results show that people tend to get closer when their relation is more intimate. In other words, social and physical distances tend to match one another. In this respect, the results match the findings of proxemics, the discipline studying the social and affective meaning of space use and organization in social gatherings. The match between results and expectations of proxemics is observed also when changing one of the most important contextual factors in this type of scenarios, namely the amount of space available to the interactants.