Aiming at the issue of friend recommendation in social network, a friend recommendation method based on multi dimensional similarity is proposed. Compared with the existing methods, it is no longer limited to a single dimension of matching information, but from three dimensions of interest, time, and space to judge the similarity of users in different dimensionality, then it uses the similarity to do comprehensive evaluation to recommend friends to the target users. Experimental studies have shown that the precision rate of recommended results is close to 70 percent, and the checking efficiency rate is close to 60 percent when the method is applied to the recommendation service of mobile social network. The performance of this method is much higher than the friend recommended method based on single dimension and can be applied to a variety of characteristics of the mobile social network.
Cao, Hongjiang and Xue, Li, "Research on the Method of Friends Recommendation in Mobile Social Network Based on Multidimensional Similarity" (2017). WHICEB 2017 Proceedings. 8.