In this paper, we look at the "social tag prediction" problem. Given a set of objects, and a set of tags applied to those objects by users, can we predict whether a given tag could/should be applied to a particular object? We investigated this question using one of the largest crawls of the social bookmarking system del.icio.us gathered to date. For URLs in del.icio.us, we predicted tags based on page text, anchor text, surrounding hosts, and other tags applied to the URL. We found an entropy-based metric which captures the generality of a particular tag and informs an analysis of how well that tag can be predicted. We also found that tag-based association rules can produce very high-precision predictions as well as giving deeper understanding into the relationships between tags. Our results have implications for both the study of tagging systems as potential information retrieval tools, and for the design of such systems.

@inproceedings{heymann2008social, author = {Heymann, Paul and Ramage, Daniel and Garcia-Molina, Hector}, title = {Social tag prediction}, booktitle = {SIGIR '08: Proceedings of the 31st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval}, publisher = {ACM}, address = {New York, NY, USA}, year = {2008}, pages = {531--538}, url = {http://portal.acm.org/citation.cfm?id=1390334.1390425}, doi = {http://doi.acm.org/10.1145/1390334.1390425}, isbn = {978-1-60558-164-4}, keywords = {folksonomy, prediction, recommender, social, tag, tagging, taggingsurvey, toread}, abstract = {In this paper, we look at the "social tag prediction" problem. Given a set of objects, and a set of tags applied to those objects by users, can we predict whether a given tag could/should be applied to a particular object? We investigated this question using one of the largest crawls of the social bookmarking system del.icio.us gathered to date. For URLs in del.icio.us, we predicted tags based on page text, anchor text, surrounding hosts, and other tags applied to the URL. We found an entropy-based metric which captures the generality of a particular tag and informs an analysis of how well that tag can be predicted. We also found that tag-based association rules can produce very high-precision predictions as well as giving deeper understanding into the relationships between tags. Our results have implications for both the study of tagging systems as potential information retrieval tools, and for the design of such systems.} }

%0 = inproceedings %A = Heymann, Paul and Ramage, Daniel and Garcia-Molina, Hector %B = SIGIR '08: Proceedings of the 31st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval %C = New York, NY, USA %D = 2008 %I = ACM %T = Social tag prediction %U = http://portal.acm.org/citation.cfm?id=1390334.1390425

Personalized recommendation is used to conquer the information overload problem, and collaborative filtering recommendation (CF) is one of the most successful recommendation techniques to date. However, CF becomes less effective when users have multiple interests, because users have similar taste in one aspect may behave quite different in other aspects. Information got from social bookmarking websites not only tells what a user likes, but also why he or she likes it. This paper proposes a division algorithm and a CubeSVD algorithm to analysis this information, distill the interrelations between different users’ various interests, and make better personalized recommendation based on them. Experiment reveals the superiority of our method over traditional CF methods. ER -

@article{keyhere, author = {Xu, Yanfei and Zhang, Liang and Liu, Wei}, title = {Cubic Analysis of Social Bookmarking for Personalized Recommendation}, journal = {Frontiers of WWW Research and Development - APWeb 2006}, year = {2006}, pages = {733--738}, url = {http://dx.doi.org/10.1007/11610113_66}, keywords = {bookmarking, folksonomy, kdubiq, recommender, social, summerschool, tagging, taggingsurvey, toread}, abstract = {Personalized recommendation is used to conquer the information overload problem, and collaborative filtering recommendation (CF) is one of the most successful recommendation techniques to date. However, CF becomes less effective when users have multiple interests, because users have similar taste in one aspect may behave quite different in other aspects. Information got from social bookmarking websites not only tells what a user likes, but also why he or she likes it. This paper proposes a division algorithm and a CubeSVD algorithm to analysis this information, distill the interrelations between different users’ various interests, and make better personalized recommendation based on them. Experiment reveals the superiority of our method over traditional CF methods. ER -} }

%0 = article %A = Xu, Yanfei and Zhang, Liang and Liu, Wei %D = 2006 %T = Cubic Analysis of Social Bookmarking for Personalized Recommendation %U = http://dx.doi.org/10.1007/11610113_66