Recommendation Method Based on Heterogeneous Information Network and Multiple Trust Relationship

A recommendation method based on heterogeneous information networks and multiple trust relationships is proposed. Firstly, the node sequence in network obtained through random walk of meta-path, representation vector each different paths generated. The user similarity meta-path by calculating spatial distance between vectors. Then, according to among users, trust-relationship calculation methods are proposed, user’s relationship fusing relationships. Finally, candidate list Microblog text two similarities achieve a personalized text. experimental results show that proposed this study superior other comparison algorithms precision, recall, F1 value NDCG value, which shows feasible when recommending