The effect of correlation coefficients on communities of recommenders Export

@inproceedings{citeulike:2747512, abstract = {Recommendation systems, based on collaborative filtering, offer a means of sifting through the enourmous amounts of content on the web by composing user ratings in order to generate predicted ratings for other users. These kinds of systems can be viewed as a network of interacting peers, where each user is a node and the links to all other nodes are weighted according to how similar the corresponding users are. Predicted ratings are generated for a user for unknown items by requesting and aggregating rating information from the surrounding neighbors. However, the different methods of computing user similarity, or weighting the network links, very often do not agree with each other, and, as a result, the structure of the network of recommenders changes completely. In this work we perform an analysis of a range of similarity measures, comparing their performance in terms of prediction accuracy and coverage. This allows us to understand the effect that similarity measures have on predicted ratings. Based on the obtained results, we argue that user-similarity may not sufficiently capture the relationships that recommenders could otherwise share in order to maximise the utility of these communities.}, address = {New York, NY, USA}, author = {Lathia, Neal and Hailes, Stephen and Capra, Licia}, booktitle = {SAC '08: Proceedings of the 2008 ACM symposium on Applied computing}, citeulike-article-id = {2747512}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1363686.1364172}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/1363686.1364172}, doi = {10.1145/1363686.1364172}, isbn = {978-1-59593-753-7}, keywords = {recommender, similarity}, location = {Fortaleza, Ceara, Brazil}, pages = {2000--2005}, posted-at = {2009-11-10 20:00:45}, priority = {3}, publisher = {ACM}, title = {The effect of correlation coefficients on communities of recommenders}, url = {http://dx.doi.org/10.1145/1363686.1364172}, year = {2008} }

TY - CONF ID - citeulike:2747512 L3 - citeulike-article-id:2747512 N2 - Recommendation systems, based on collaborative filtering, offer a means of sifting through the enourmous amounts of content on the web by composing user ratings in order to generate predicted ratings for other users. These kinds of systems can be viewed as a network of interacting peers, where each user is a node and the links to all other nodes are weighted according to how similar the corresponding users are. Predicted ratings are generated for a user for unknown items by requesting and aggregating rating information from the surrounding neighbors. However, the different methods of computing user similarity, or weighting the network links, very often do not agree with each other, and, as a result, the structure of the network of recommenders changes completely. In this work we perform an analysis of a range of similarity measures, comparing their performance in terms of prediction accuracy and coverage. This allows us to understand the effect that similarity measures have on predicted ratings. Based on the obtained results, we argue that user-similarity may not sufficiently capture the relationships that recommenders could otherwise share in order to maximise the utility of these communities. CY - Fortaleza, Ceara, Brazil SN - 978-1-59593-753-7 AD - New York, NY, USA EP - 2005 TI - The effect of correlation coefficients on communities of recommenders PB - ACM T2 - SAC '08: Proceedings of the 2008 ACM symposium on Applied computing SP - 2000 KW - recommender KW - similarity AU - Lathia, Neal AU - Hailes, Stephen AU - Capra, Licia PY - 2008/// UR - http://dx.doi.org/10.1145/1363686.1364172 ER -