Toward Modeling Commensal Interactions in Human Dyads

Wepostulate the need for the creation of computational methods to model interactions specific to commensal settings. They would be used to analyze and quantify interactions during shared meals, and to design new devices for commensality. To illustrate the concept, we present algorithms for measuring: 1) food intake ratio and synchronization, and 2) smile ratio and synchronization in pairs of eaters. They process images of two commensals captured simultaneously to extract information specific to their nonverbal behaviors and subsequently apply the Event Synchronization algorithm to compute their degree of synchronization. Next, we test the proposed methods on videos of 12 dyads sharing meals. Our findings suggest that the self-reported strength of the relationship is positively correlated with the degree of food intake synchronization and inversely correlated with the quantity of smiles. We conclude by discussing potential applications for developing artificial companions to support solo eaters.