SURVEY ON TRUST AWARE RECOMMENDATION

Abstract

Now-a-days social networking sites are more and more popular for the communication, networking and content sharing. In the online social networks, social network based recommendation approach is used. In the paper, we study recommendation techniques such as Matrix Factorization (MF) for the Trust Aware Recommendation in Social networks based on the Deep Learning (DL) called as deep learning based matrix factorization (DLMF). Firstly, find out the per-train initial value of the parameter for this using a deep auto-encoder. The community detection algorithm based on trust relations in social networks is proposed for the revamp the MF model with social trust ensemble and community effect. A benefit of such approaches is that the ability of dealing with problems with clod star users.