Abstract
Online social networks like Facebook recommend new friends to users based on an explicit social network that users build by adding each other as friends. The majority of earlier work in link prediction infers new interactions between users by mainly focusing on a single network type. However, users also form several implicit social networks through their daily interactions like commenting on people's posts or rating similarly the same products. Prior work primarily exploited both explicit and implicit social networks to tackle the group/item recommendation problem that recommends to users groups to join or items to buy. In this paper, we show that auxiliary information from the user-item network fruitfully combines with the friendship network to enhance friend recommendations. We transform the well-known Katz algorithm to utilize a multi-modal network and provide friend recommendations. We experimentally show that the proposed method is more accurate in recommending friends when compared with two single source path-based algorithms using both synthetic and real data sets.