Fortunately, with the popularity and rapid
development of social networks, more and more users enjoy sharing their
experiences, reviews, ratings, photos, and moods with their friends. Many
social-based model have been proposed to improve the performance of recommender
system. Yanget al propose to use the concept of ‘inferred trust
circle based on the domain-obvious of circles of friends on social networks to
recommend users favorite items. Jianget al prove that
individual preference is also an important factor in social networks.
In their Context Model, user latent features
should be similar to his/her friends’ according to preference similarity.
Hu et al. and Lei etal utilize the
power of semantic knowledge bases to handle textual messages and
The first generation of recommender systems
with traditional collaborative filtering algorithms is facing great challenges
of cold start for users (new users in the recommender system with little
historical records) and the sparsity of datasets.
They perform biases based matrix factorization
Matrix Factorization (MF) is one of the
most popular methods for recommender systems. It offers much flexibility for
modeling various real-life situations, such as allowing incorporation of additional
geographical and social information. Therefore, in this paper, the popular
matrix factorization is utilized to learn the latent features of users and
items. Some major approaches based on probabilistic matrix factorization are
introduced as follows.
Algorithm of location based rating prediction model LBRP
? (t) = ? (U (t), P (t)), t= 0.
2) Set parameters: k, l, n, ?1, ?2, ?, ?, ?