A0596
Title: Preference learning across social networks for recommendations
Authors: Yipeng Zhuang - The Education University of Hong Kong (Hong Kong)
Philip Yu - The Education University of Hong Kong (Hong Kong) [presenting]
Abstract: Preference learning refers to the problem of learning from preference data, which can ultimately understand individuals' preference behaviors. A typical problem is personalized item recommendation where users in a social media platform rated a set of items and their preferences may be influenced by their peers or friends in a social network. However, not all items were rated and many of these ratings are missing. We propose novel models for learning incomplete preferences of items across social networks. Finally, we apply our models to various big datasets on personalized movie recommendations with the goal of better prediction of the ratings of unrated movies for possible recommendation.
