Inverse Foraging

Users' engagement with pervasive displays has been extensively studied, however, determining how their content is interesting remains an open problem. Tracking of body postures and gaze explored as indication attention; still, existing works have not able to estimate the interest passers-by from readily available data, such display viewing time. This article presents a simple yet accurate method estimating users' in multiple items shown at same time on displays. The proposed approach builds information foraging theory, which assumes that users optimally decide they consume. Through inverse foraging, parameters model are fitted values times observed practice, yield estimates user interest. Different models evaluated by using synthetic data controlled study. results demonstrate accurately interest, achieving R2 above 70% comparison self-reported As consequence, solution allows dynamically adapt displays, based can be easily obtained field deployments.