@misc{cattuto-2007,
  author = {Cattuto, Ciro and Baldassarri, Andrea and Servedio, Vito D. P. and Loreto, Vittorio},
  interhash = {7de017393b2d48335e209a9db23e08b6},
  intrahash = {4d6bfbd16ba976f4a4aae985c2a92449},
  title = {Vocabulary growth in collaborative tagging systems},
  url = {http://www.citebase.org/abstract?id=oai:arXiv.org:0704.3316},
  year = 2007
}

@article{isafolksonomy2007fwn,
  author = {Noruzi, Alireza},
  interhash = {406153e7b2a8c11a963d7f14718f02d7},
  intrahash = {eaef17fef76ad3152f0300a5e9d5ddae},
  journal = {Webology},
  number = 2,
  title = {{Folksonomies: Why do we need controlled vocabulary?}},
  url = {http://www.webology.ir/2007/v4n2/editorial12.html},
  volume = 4,
  year = 2007
}

@inproceedings{1180904,
  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.},
  address = {New York, NY, USA},
  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},
  booktitle = {CSCW '06: Proceedings of the 2006 20th anniversary conference on Computer supported cooperative work},
  doi = {http://doi.acm.org/10.1145/1180875.1180904},
  interhash = {96b20bffcbc91e528461529935524b90},
  intrahash = {582641c05e7a0b9396945a951822c83f},
  isbn = {1-59593-249-6},
  location = {Banff, Alberta, Canada},
  pages = {181--190},
  publisher = {ACM},
  title = {tagging, communities, vocabulary, evolution},
  url = {http://portal.acm.org/citation.cfm?id=1180904},
  year = 2006
}

@inproceedings{1180904,
  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.},
  address = {New York, NY, USA},
  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},
  booktitle = {CSCW '06: Proceedings of the 2006 20th anniversary conference on Computer supported cooperative work},
  doi = {http://doi.acm.org/10.1145/1180875.1180904},
  interhash = {96b20bffcbc91e528461529935524b90},
  intrahash = {582641c05e7a0b9396945a951822c83f},
  isbn = {1-59593-249-6},
  location = {Banff, Alberta, Canada},
  pages = {181--190},
  publisher = {ACM},
  title = {tagging, communities, vocabulary, evolution},
  url = {http://portal.acm.org/citation.cfm?id=1180904},
  year = 2006
}

@inproceedings{sen2006tagging,
  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.},
  address = {New York, NY, USA},
  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},
  booktitle = {CSCW '06: Proceedings of the 2006 20th anniversary conference on Computer supported cooperative work},
  doi = {http://doi.acm.org/10.1145/1180875.1180904},
  interhash = {96b20bffcbc91e528461529935524b90},
  intrahash = {582641c05e7a0b9396945a951822c83f},
  isbn = {1-59593-249-6},
  location = {Banff, Alberta, Canada},
  pages = {181--190},
  publisher = {ACM},
  title = {tagging, communities, vocabulary, evolution},
  url = {http://portal.acm.org/citation.cfm?id=1180904},
  year = 2006
}

@article{ciro2006semiotic,
  abstract = {Abstract  A distributed classification paradigm known as collaborative tagging has been successfully deployed in large-scale web applications designed to manage and share diverse online resources. Users of these applications organize resources by associating with them freely chosen text labels, or tags. Here we regard tags as basic dynamical entities and study the semiotic dynamics underlying collaborative tagging. We collect data from a popular system and focus on tags associated with a given resource.We find that the frequencies of tags obey to a generalized Zipf’s law and show that a Yule–Simon process with memory can beused to explain the observed frequency distributions in terms of a simple model of user behavior},
  author = {Cattuto, Ciro},
  interhash = {6651fe8b8916e8407f738325c092b860},
  intrahash = {86a43b0d0b4956b3ff6b553f78277ec9},
  journal = {The European Physical Journal C - Particles and Fields},
  month = {#aug#},
  number = 0,
  pages = {33--37},
  title = {Semiotic dynamics in online social communities},
  url = {http://dx.doi.org/10.1140/epjcd/s2006-03-004-4},
  volume = 46,
  year = 2006
}

@article{cattuto2007growth,
  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. },
  author = {Cattuto, Ciro and Baldassarri, Andrea and Servedio, Vito Domenico Pietro and Loreto, Vittorio},
  interhash = {7de017393b2d48335e209a9db23e08b6},
  intrahash = {04bc17658d8d028e01d69123b5dc6b40},
  journal = {CoRR},
  month = apr,
  note = {arXiv:0704.3316v1},
  title = {Vocabulary growth in collaborative tagging systems},
  url = {http://arxiv.org/abs/0704.3316},
  volume = {abs/0704.3316},
  year = 2007
}

@inproceedings{ilprints956,
  abstract = {A fundamental premise of tagging systems is that regular users can organize large collections for browsing and other tasks using uncontrolled vocabularies. Until now, that premise has remained relatively unexamined. Using library data, we test the tagging approach to organizing a collection. We find that tagging systems have three major large scale organizational features: consistency, quality, and completeness. In addition to testing these features, we present results suggesting that users produce tags similar to the topics designed by experts, that paid tagging can effectively supplement tags in a tagging system, and that information integration may be possible across tagging systems.},
  author = {Heymann, Paul and Paepcke, Andreas and Garcia-Molina, Hector},
  booktitle = {Third ACM International Conference on Web Search and Data Mining (WSDM2010)},
  interhash = {d4f72ed57e6b99dbe32e18e218d81ef5},
  intrahash = {6aaa478f3700f435ec3a1c1cba0046da},
  month = {February},
  pages = {1--10},
  publisher = {Stanford University},
  title = {Tagging Human Knowledge},
  url = {http://ilpubs.stanford.edu:8090/956/},
  year = 2010
}

@inproceedings{heymann2009contrasting,
  abstract = {Social cataloging sites---tagging systems where users tag books---provide us with a rare opportunity to contrast tags to other information organization systems. We contrast tags to a controlled vocabulary, the Library of Congress Subject Headings, which has been developed over several decades. We find that many of the keywords designated by tags and LCSH are similar or the same, but that usage of keywords by annotators is quite different. },
  author = {Heymann, Paul and Garcia-Molina, Hector},
  booktitle = {Second ACM International Conference on Web Search and Data Mining (WSDM 2009), Late Breaking Results Session},
  interhash = {593bb7c35aa6a3a90863c920b6eb7481},
  intrahash = {7a9851b13e821086676810a596fba4cb},
  month = feb,
  pages = {1--4},
  publisher = {Stanford InfoLab},
  title = {Contrasting Controlled Vocabulary and Tagging: Do Experts Choose the Right Names to Label the Wrong Things?},
  url = {http://ilpubs.stanford.edu:8090/955/},
  year = 2009
}

@inproceedings{sen2006tagging,
  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.},
  address = {New York, NY, USA},
  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},
  booktitle = {CSCW '06: Proceedings of the 2006 20th anniversary conference on Computer supported cooperative work},
  doi = {10.1145/1180875.1180904},
  file = {sen2006tagging.pdf:sen2006tagging.pdf:PDF},
  groups = {public},
  interhash = {96b20bffcbc91e528461529935524b90},
  intrahash = {582641c05e7a0b9396945a951822c83f},
  isbn = {1-59593-249-6},
  location = {Banff, Alberta, Canada},
  pages = {181--190},
  publisher = {ACM},
  timestamp = {2011-02-02 15:10:48},
  title = {tagging, communities, vocabulary, evolution},
  url = {http://portal.acm.org/citation.cfm?id=1180904},
  username = {dbenz},
  year = 2006
}

@inproceedings{cattuto2007vocabulary,
  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.},
  author = {Cattuto, Ciro and Baldassarri, Andrea and Servedio, Vito D. P. and Loreto, Vittorio},
  interhash = {7de017393b2d48335e209a9db23e08b6},
  intrahash = {fb163dd424fa1eb40640340f27ee0ea4},
  title = {Vocabulary growth in collaborative tagging systems},
  url = {http://www.citebase.org/abstract?id=oai:arXiv.org:0704.3316},
  year = 2007
}

@article{furnas1987vocabulary,
  acmid = {32212},
  address = {New York, NY, USA},
  author = {Furnas, G. W. and Landauer, T. K. and Gomez, L. M. and Dumais, S. T.},
  doi = {10.1145/32206.32212},
  interhash = {b03603efa8152234684ffce8b44a5abb},
  intrahash = {1a6e34f9b367fcfc67454607a9b2f8e3},
  issn = {0001-0782},
  issue = {11},
  journal = {Commun. ACM},
  month = {November},
  numpages = {8},
  pages = {964--971},
  publisher = {ACM},
  title = {The vocabulary problem in human-system communication},
  url = {http://doi.acm.org/10.1145/32206.32212},
  volume = 30,
  year = 1987
}

@inproceedings{carman2009statistical,
  abstract = {We investigate tag and query logs to see if the terms people use to annotate websites are similar to the ones they use to query for them. Over a set of URLs, we compare the distribution of tags used to annotate each URL with the distribution of query terms for clicks on the same URL. Understanding the relationship between the distributions is important to determine how useful tag data may be for improving search results and conversely, query data for improving tag prediction. In our study, we compare both term frequency distributions using vocabulary overlap and relative entropy. We also test statistically whether the term counts come from the same underlying distribution. Our results indicate that the vocabulary used for tagging and searching for content are similar but not identical. We further investigate the content of the websites to see which of the two distributions (tag or query) is most similar to the content of the annotated/searched URL. Finally, we analyze the similarity for different categories of URLs in our sample to see if the similarity between distributions is dependent on the topic of the website or the popularity of the URL.},
  acmid = {1571965},
  address = {New York, NY, USA},
  author = {Carman, Mark J. and Baillie, Mark and Gwadera, Robert and Crestani, Fabio},
  booktitle = {Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval},
  doi = {10.1145/1571941.1571965},
  interhash = {d023f082cc783251a90a2f71c71826eb},
  intrahash = {d3e4319a20670f7f73bdf83b63bdf4c7},
  isbn = {978-1-60558-483-6},
  location = {Boston, MA, USA},
  numpages = {8},
  pages = {123--130},
  publisher = {ACM},
  series = {SIGIR '09},
  title = {A statistical comparison of tag and query logs},
  url = {http://doi.acm.org/10.1145/1571941.1571965},
  year = 2009
}