Development of a hybrid recommendation approach based on item content and user social influence

摘要

With the development of E-commerce and social media, personalized recommendation service becomes more and more important to both companies and users. In this paper, we propose a hybrid recommendation approach based on items' content and users' social influence. On the basis of social influence network and opinion formation models, we suggest that a user's preference for an item is the combination of his/her own consideration for the item, direct influence imposed by the neighborhood, and indirect influence exerted by public opinion through social interactions. Furthermore, we distinguish direct influence into persuasive influence and supportive influence and discuss the effectiveness to take into account the combined effect of these two types of influence.