Exploring a human centered approach to managing visual privacy concerns during collaboration

Human Centered Computing (HCC) systems should be socially aware and HCC applications should act according to the social context in which they are deployed. This paper examines a human centered approach to managing visual privacy during collaboration around a personal computer. We propose an intelligent system that takes into account the current social context of the user. Prior research has found that visual privacy can be a concern when traces of prior activities (i.e. web browsing history) that are inappropriate for the current social viewing context are displayed. Investigations of privacy management approaches have found that the burden of manually classifying traces of prior activity is high. The approach presented here is based on a conceptual model of incidental information privacy in web browsers developed previously. In this paper, we introduce a predictive model of privacy concerns, both for the general case and within the context of two specific viewer types. Our results suggest that an intelligent user interface approach is feasible and that adaptations may be combined with more explicit approaches to reduce users' burden of managing their visual privacy.