Learning from User Interactions for Recommending Content in Social Media

摘要: We study the problem of recommending hyperlinks to users in social media form status updates. start with a candidate set links posted by user's circle e.g., friends, followers and rank these using combination ii¾?a user interaction model, iii¾?the similarity profile link. Experiments on two datasets demonstrate that our method is robust and, average, outperforms, strong chronological baseline.