|
|
|
                                          
|
Return to Session VIIIa: Content-based filtering & collaborative filtering
Information filtering has made considerable progress in recent years. The predominant approaches are content-based methods and collaborative methods. Researchers have largely concentrated on either of the two approaches since a principled unifying framework is still lacking. This paper suggests that both approaches can be combined under a hierarchical Bayesian framework. Individual content-based user profiles are generated and collaboration between various user models is achieved via a common learned prior distribution. However, it turns out that a parametric distribution (e.g. Gaussian) is too restrictive to describe such a common learned prior distribution. We thus introduce a nonparametric common prior, which is a sample generated from a Dirichlet process which assumes the role of a hyper prior. We describe effective means to learn this nonparametric distribution, and apply it to learn users' information needs. The resultant algorithm is simple and understandable, and offers a principled solution to combine content-based filtering and collaborative filtering. Within our framework, we are now able to interpret various existing techniques from a unifying point of view. Finally we demonstrate the empirical success of the proposed information filtering methods.
@inproceedings{1009053, author = {Kai Yu and Volker Tresp and Shipeng Yu}, title = {A nonparametric hierarchical bayesian framework for information filtering}, booktitle = {SIGIR '04: Proceedings of the 27th annual international conference on Research and development in information retrieval}, year = {2004}, isbn = {1-58113-881-4}, pages = {353--360}, location = {Sheffield, United Kingdom}, doi = {http://doi.acm.org/10.1145/1008992.1009053}, publisher = {ACM Press}, }  ©2005 Association for Computing Machinery |
