Several matrix factorization methods have
recently been proposed.26 The matrix approximation
models all focus on representing the
user-item rating matrix with low-dimensional
latent vectors. Recognizing that influence is a
subtle force that governs the dynamics of social
networks, influence-based recommendation27
involves interpersonal influence in social recommendation
cases. Trust-based approaches
exploit the trust network among users and
make recommendations based on the ratings of
users who are directly or indirectly trusted.