Hierarchical Bayesian Networks have also been used in several settings as a way
to add domain-knowledge for information filtering [78]. One of the issues with hier
arc hical Bayesian networks, however, is that it is very expensive to learn and update
the model when there are many users in it. Zhang and Koren [79] propose a varia-
tion over the standard Expectation-Maximization (EM) model in order to speed up
this process in the scenario of a content-based RS.