Learning to recommend with social contextual information from implicit feedback

Recommender systems with social networks have been well studied in recent years. However, most of these methods ignore the social contextual information among users and items, which is significant and useful for predicting users’ preferences in many recommendation problems. Moreover, most existing social recommendation methods have been proposed for the scenarios where users can provide explicit ratings. But in fact, the explicit feedback is not always available, most of the feedback in real social networks is not explicit but implicit. Motivated by above observations, we propose a unified ranking framework fusing social contextual information and common social relations for implicit feedback. Specifically, we first extend the user latent features by the implicit interest deduced from social context, and then we integrate the common social relations as factorization terms to further improve recommendation quality. Finally, we optimize our model in a Bayesian personalized ranking framework. The experiments on real-world dataset show that our approach outperforms the other state-of-the-art algorithms in terms of AUC, NDCG and Pre@3. This result demonstrates the importance of social context and common social relations for the formation of the implicit ratings.