Skip to Main Content
With the increasing amount of research on smart TVs, users are interacting with them in an evermore convenient way. However, current program recommendations mainly focus on using individual profiles and require users' active participation when multiple viewers coexist. In this paper, we propose a socially aware program recommender for multiple viewers of a digital TV that rates and selects TV programs based on individual and group preferences. For this task, the proposed recommender generates recommendations for users by merging user profiles and combining their common interests. In this way, programs that all users prefer are automatically selected and ambiguous or conflicting programs are mediated based on user feedback. Through subsequent experiments with a smart TV equipped with the program recommender, we found that the performance of group recommendations improved when individual profiles and the group's common interests were used, and that users preferred different strategies when they were with other people.
Date of Publication: May 2009