We analyze a large-scale snapshot of del.icio.us and investigate how the number of different tags in the system grows as a function of a suitably defined notion of time. We study the temporal evolution of the global vocabulary size, i.e. the number of distinct tags in the entire system, as well as the evolution of local vocabularies, that is the growth of the number of distinct tags used in the context of a given resource or user. In both cases, we find power-law behaviors with exponents smaller than one. Surprisingly, the observed growth behaviors are remarkably regular throughout the entire history of the system and across very different resources being bookmarked. Similar sub-linear laws of growth have been observed in written text, and this qualitative universality calls for an explanation and points in the direction of non-trivial cognitive processes in the complex interaction patterns characterizing collaborative tagging.

@inproceedings{cattuto2007vocabulary, author = {Cattuto, Ciro and Baldassarri, Andrea and Servedio, Vito D. P. and Loreto, Vittorio}, title = {Vocabulary growth in collaborative tagging systems}, year = {2007}, url = {http://www.citebase.org/abstract?id=oai:arXiv.org:0704.3316}, keywords = {vocabulary, folksonomy, toread, analysis}, abstract = { We analyze a large-scale snapshot of del.icio.us and investigate how the number of different tags in the system grows as a function of a suitably defined notion of time. We study the temporal evolution of the global vocabulary size, i.e. the number of distinct tags in the entire system, as well as the evolution of local vocabularies, that is the growth of the number of distinct tags used in the context of a given resource or user. In both cases, we find power-law behaviors with exponents smaller than one. Surprisingly, the observed growth behaviors are remarkably regular throughout the entire history of the system and across very different resources being bookmarked. Similar sub-linear laws of growth have been observed in written text, and this qualitative universality calls for an explanation and points in the direction of non-trivial cognitive processes in the complex interaction patterns characterizing collaborative tagging.} }

%0 = inproceedings %A = Cattuto, Ciro and Baldassarri, Andrea and Servedio, Vito D. P. and Loreto, Vittorio %D = 2007 %T = Vocabulary growth in collaborative tagging systems %U = http://www.citebase.org/abstract?id=oai:arXiv.org:0704.3316

A tagging community's vocabulary of tags forms the basis for social navigation and shared expression.We present a user-centric model of vocabulary evolution in tagging communities based on community influence and personal tendency. We evaluate our model in an emergent tagging system by introducing tagging features into the MovieLens recommender system.We explore four tag selection algorithms for displaying tags applied by other community members. We analyze the algorithms 'effect on vocabulary evolution, tag utility, tag adoption, and user satisfaction.

@inproceedings{sen2006tagging, author = {Sen, Shilad and Lam, Shyong K. and Rashid, Al Mamunur and Cosley, Dan and Frankowski, Dan and Osterhouse, Jeremy and Harper, F. Maxwell and Riedl, John}, title = {tagging, communities, vocabulary, evolution}, booktitle = {CSCW '06: Proceedings of the 2006 20th anniversary conference on Computer supported cooperative work}, publisher = {ACM}, address = {New York, NY, USA}, year = {2006}, pages = {181--190}, url = {http://portal.acm.org/citation.cfm?id=1180904}, doi = {10.1145/1180875.1180904}, isbn = {1-59593-249-6}, keywords = {ol_web2.0, tagging, vocabulary, background}, abstract = {A tagging community's vocabulary of tags forms the basis for social navigation and shared expression.We present a user-centric model of vocabulary evolution in tagging communities based on community influence and personal tendency. We evaluate our model in an emergent tagging system by introducing tagging features into the MovieLens recommender system.We explore four tag selection algorithms for displaying tags applied by other community members. We analyze the algorithms 'effect on vocabulary evolution, tag utility, tag adoption, and user satisfaction.} }

%0 = inproceedings %A = Sen, Shilad and Lam, Shyong K. and Rashid, Al Mamunur and Cosley, Dan and Frankowski, Dan and Osterhouse, Jeremy and Harper, F. Maxwell and Riedl, John %B = CSCW '06: Proceedings of the 2006 20th anniversary conference on Computer supported cooperative work %C = New York, NY, USA %D = 2006 %I = ACM %T = tagging, communities, vocabulary, evolution %U = http://portal.acm.org/citation.cfm?id=1180904

@article{furnas1987vocabulary, author = {Furnas, G. W. and Landauer, T. K. and Gomez, L. M. and Dumais, S. T.}, title = {The vocabulary problem in human-system communication}, journal = {Commun. ACM}, publisher = {ACM}, address = {New York, NY, USA}, year = {1987}, volume = {30}, pages = {964--971}, url = {http://doi.acm.org/10.1145/32206.32212}, doi = {10.1145/32206.32212}, issn = {0001-0782}, keywords = {problem, tagging, vocabulary} }

%0 = article %A = Furnas, G. W. and Landauer, T. K. and Gomez, L. M. and Dumais, S. T. %C = New York, NY, USA %D = 1987 %I = ACM %T = The vocabulary problem in human-system communication %U = http://doi.acm.org/10.1145/32206.32212