Shang, Ming-Sheng Jin, Ci-Hang Zhou, Tao Zhang, Yi-Cheng 2009-08-15 In this paper, by applying a diffusion process, we propose a new index to quantify the similarity between two users in a user–object bipartite graph. To deal with the discrete ratings on objects, we use a multi-channel representation where each object is mapped to several channels with the number of channels being equal to the number of different ratings. Each channel represents a certain rating and a user having voted an object will be connected to the channel corresponding to the rating. Diffusion process taking place on such a user–channel bipartite graph gives a new similarity measure of user pairs, which is further demonstrated to be more accurate than the classical Pearson correlation coefficient under the standard collaborative filtering framework. application/pdf https://folia.unifr.ch/global/documents/301495 https://folia.unifr.ch/documents/301495/files/zhang_cfb.pdf eng info:eu-repo/semantics/altIdentifier/doi/10.1016/j.physa.2009.08.011 info:eu-repo/semantics/openAccess License undefined Physica A: Statistical Mechanics and its Applications. - 2009, vol. 388, no. 23, p. 4867-4871 Recommender systems Collaborative filtering Diffusion-based similarity Complex networks Infophysics info:eu-repo/classification/udc/53 Collaborative filtering based on multi-channel diffusion http://purl.org/coar/resource_type/c_6501