@inproceedings{Caverlee2008:LargeScaleStudyMySpace,
  author = {Caverlee, James and Webb, Steve},
  booktitle = {Proceedings from the 2nd International Conference on Weblogs and Social Media (AAAI)},
  comment = {"Nearly half of the profiles on MySpace have been abandoned"

"While young users (in their teens and 20s) are most prevalent
on MySpace, women who are most prevalent at the
youngest ages (14 to 20), whereas men are most prevalent
for all other ages (21 and up)."

"Overall, the fraction of private profiles is increasing with
time"},
  interhash = {ab4c8bedf5831ad03abacd1c25b87a03},
  intrahash = {56c414dfc572c2b0c5cbf48458c744b5},
  posted-at = {2009-01-01 22:53:24},
  priority = {2},
  title = {A Large-Scale Study of MySpace:
Observations and Implications for Online Social Networks},
  url = {http://faculty.cs.tamu.edu/caverlee/pubs/caverlee08alarge.pdf},
  year = 2008
}

@inproceedings{narayanan2008robust,
  abstract = {We present a new class of statistical de- anonymization attacks against high-dimensional micro-data, such as individual preferences, recommendations, transaction records and so on. Our techniques are robust to perturbation in the data and tolerate some mistakes in the adversary's background knowledge. We apply our de-anonymization methodology to the Netflix Prize dataset, which contains anonymous movie ratings of 500,000 subscribers of Netflix, the world's largest online movie rental service. We demonstrate that an adversary who knows only a little bit about an individual subscriber can easily identify this subscriber's record in the dataset. Using the Internet Movie Database as the source of background knowledge, we successfully identified the Netflix records of known users, uncovering their apparent political preferences and other potentially sensitive information.},
  author = {Narayanan, Arvind and Shmatikov, Vitaly},
  booktitle = {Proc. of the 29th IEEE Symposium on Security and Privacy},
  doi = {10.1109/SP.2008.33},
  interhash = {77c86be6c4bf7fc51b7faecfe85479fe},
  intrahash = {2748ba4684dbe09120aee56c6a0a9de9},
  issn = {1081-6011},
  month = may,
  pages = {111--125},
  publisher = {IEEE Computer Society},
  title = {Robust De-anonymization of Large Sparse Datasets},
  url = {http://www.cs.utexas.edu/~shmat/shmat_oak08netflix.pdf},
  year = 2008
}

@inproceedings{HaHe06,
  abstract = {Tagging-based systems enable users to categorize web resources by  means of tags (freely chosen keywords), in order to re-finding these  resources later. Tagging is implicitly also a social indexing process,  since users share their tags and resources, constructing a social  tag index, so-called folksonomy. At the same time of tagging-based  system, has been popularised an interface model for visual information  retrieval known as Tag-Cloud. In this model, the most frequently  used tags are displayed in alphabetical order. This paper presents  a novel approach to Tag-Cloud�s tags selection, and proposes the  use of clustering algorithms for visual layout, with the aim of improve  browsing experience. The results suggest that presented approach  reduces the semantic density of tag set, and improves the visual  consistency of Tag-Cloud layout.},
  author = {Hassan-Montero, Y. and Herrero-Solana, V.},
  booktitle = {InScit2006: International Conference on Multidisciplinary Information  Sciences and Technologies},
  file = {HaHe06.pdf:folksonomies\\HaHe06.pdf:PDF},
  interhash = {4458142370e3c6a4fe656af2f822a0dc},
  intrahash = {06f68f9fe46dc6d0f646d932e428dec9},
  misc = {comment = {proposes using k-clustering and some sort of semantic sorting  to refactor tag cloud layout to improve browsing. Not clear on how  they actually do it.}, priority = {0}, citeulike-article-id = {2045619}},
  owner = {michael},
  timestamp = {2008.01.14},
  title = {Improving Tag-Clouds as Visual Information Retrieval Interfaces},
  url = {http://nosolousabilidad.com/hassan/improving_tagclouds.pdf},
  year = 2006
}

@article{1751-8121-41-22-224016,
  abstract = {We analyze CiteULike, an online collaborative tagging system where users bookmark and annotate scientific papers. Such a system can be naturally represented as a tri-partite graph whose nodes represent papers, users and tags connected by individual tag assignments. The semantics of tags is studied here, in order to uncover the hidden relationships between tags. We find that the clustering coefficient can be used to analyze the semantical patterns among tags.},
  author = {Capocci, Andrea and Caldarelli, Guido},
  interhash = {14c8ecbc38dcdae876c3f4401006e3bb},
  intrahash = {2a219a2664c566b405420f720583643a},
  journal = {Journal of Physics A: Mathematical and Theoretical},
  number = 22,
  pages = {224016 (7pp)},
  title = {Folksonomies and clustering in the collaborative system CiteULike},
  url = {http://stacks.iop.org/1751-8121/41/224016},
  volume = 41,
  year = 2008
}

@inproceedings{1458098,
  address = {New York, NY, USA},
  author = {Song, Yang and Zhang, Lu and Giles, C. Lee},
  booktitle = {CIKM '08: Proceeding of the 17th ACM conference on Information and knowledge mining},
  doi = {http://doi.acm.org/10.1145/1458082.1458098},
  interhash = {5c03bc1e658b6d44f053944418bdaec3},
  intrahash = {d330a3537b4a14fbd40661424ec8e465},
  isbn = {978-1-59593-991-3},
  location = {Napa Valley, California, USA},
  pages = {93--102},
  publisher = {ACM},
  title = {A sparse gaussian processes classification framework for fast tag suggestions},
  url = {http://portal.acm.org/citation.cfm?id=1458098},
  year = 2008
}