Academic Social Network Scholars Recommendation Model Based on Community Division

In order to solve the problem of subset community in some community detection algorithms which is based on label propagation, this paper proposes a method that merges the core network in advance, and constructs a scholars recommendation model for academic social network. The model processes the problem of subset community through the GraphChi framework in parallel and recommends the scholar users within the community according to the relevant recommendation rules to achieve the scholars' recommendation service. Experimental results show that the proposed model effectively reduces the running time of community detection algorithm and achieves good recommendation results.