Network-Centric Recommendation: Personalization with and in Social Networks

People often rely on the collective intelligence of their social network for making choices, which in turn influences their preferences and decisions. However, traditional recommender systems largely ignore social context, and even network-aware recommenders don´t explicitly support social goals and concerns such as shared consumption and identity management. We present relevant theories and research questions for a more network-centric approach to recommendations and introduce Pop Core, a platform for studying them in Face book. An initial 50-user study with Pop Core gives insights into tradeoffs around the popularity, likeability, and rateability of recommendations made by a set of network-centric algorithms and to people´s thoughts about the idea of network-centric recommendation.