"we discovered regularities in user activity, tag frequencies, kinds of tags used, bursts of popularity in bookmarking and a remarkable stability in the relative proportions of tags within a given url. We also present a dynamical model of collaborative ta
M. Nentwich. ita-Manuskript, ita-09-02. Institut für Technikfolgen-Abschätzung an der Österreichischen Akademie der Wissenschaften, Wien, (November 2009)
D. Parra, and P. Brusilovsky. RecSys '09: Proceedings of the third ACM conference on Recommender systems, page 237--240. New York, NY, USA, ACM, (2009)