@inproceedings{brooks2006improved,
  abstract = {Tags have recently become popular as a means of annotating and organizing Web pages and blog entries. Advocates of tagging argue that the use of tags produces a 'folksonomy', a system in which the meaning of a tag is determined by its use among the community as a whole. We analyze the effectiveness of tags for classifying blog entries by gathering the top 350 tags from Technorati and measuring the similarity of all articles that share a tag. We find that tags are useful for grouping articles into broad categories, but less effective in indicating the particular content of an article. We then show that automatically extracting words deemed to be highly relevant can produce a more focused categorization of articles. We also show that clustering algorithms can be used to reconstruct a topical hierarchy among tags, and suggest that these approaches may be used to address some of the weaknesses in current tagging systems.},
  address = {New York, NY, USA},
  author = {Brooks, Christopher H. and Montanez, Nancy},
  booktitle = {WWW '06: Proceedings of the 15th international conference on World Wide Web},
  file = {:brooks06-improved.pdf:PDF;brooks2006improved.pdf:brooks2006improved.pdf:PDF},
  groups = {public},
  interhash = {c88a665abf8d88c5a7ae95fa2783f837},
  intrahash = {5c9c83e89da2faa8906a5927fe7ca3ef},
  lastdatemodified = {2006-07-18},
  lastname = {Brooks},
  longnotes = {[[http://www2006.org/programme/files/pdf/583-slides.pdf slides]] Summary: - authors analyse the effectiveness of tags for classifying blog articles (technorati) - clustering of articles beloning to top 350 technorati tags * by tag * randomly * by related by Google News - results: * tags help to classify articles into broad categories (yet Google News performs better) * tags are not that descriptive for a specific topic of an article * automatically extracted tags (by TF/IDF) are much more descriptive for specific content - 2nd study: hierarchical clustering of articles (starting from tag clusters, i.e. all articles who share a tag) - resulting tag hierarchy comes close to e.g. Yahoo hand-built one},
  own = {own},
  pages = {625--632},
  pdf = {brooks06-improved.pdf},
  publisher = {ACM Press},
  read = {read},
  timestamp = {2009-09-29 16:23:07},
  title = {Improved annotation of the blogosphere via autotagging and hierarchical clustering},
  url = {http://www2006.org/programme/item.php?id=583},
  username = {dbenz},
  year = 2006
}

@inproceedings{brooks2005analysis,
  abstract = {Tags have recently become popular as a means of annotating and organizing Web pages and blog entries. Advocates of tagging argue that the use of tags produces a 'folksonomy', a system in which the meaning of a tag is determined by its use among the community as a whole. We analyze the effectiveness of tags for classifying blog entries by gathering the top 350 tags from Technorati and measuring the similarity of all articles that share a tag. We find that tags are useful for grouping articles into broad categories, but less effective in indicating the particular content of an article. We then show that automatically extracting words deemed to be highly relevant can produce more focused categorization of articles. We also provide anecdotal evidence of some of tagging's weaknesses, and discuss future directions that could make tagging more effective as a tool for information organization and retrieval.},
  author = {Brooks, Christopher H. and Montanez, Nancy},
  booktitle = {AAAI Spring Symposium on Computational Approaches to Analyzing Weblogs},
  interhash = {71c1300be554e03e62db313f15fa1a27},
  intrahash = {e6c9ec01018cf315ca5c49461de86c51},
  month = mar,
  organization = {AAAI},
  title = {An analysis of the effectiveness of tagging in blogs},
  url = {http://www.aaai.org/Library/Symposia/Spring/2006/ss06-03-002.php},
  year = 2005
}

@inproceedings{1135869,
  address = {New York, NY, USA},
  author = {Brooks, Christopher H. and Montanez, Nancy},
  booktitle = {WWW '06: Proceedings of the 15th international conference on World Wide Web},
  doi = {http://doi.acm.org/10.1145/1135777.1135869},
  interhash = {c88a665abf8d88c5a7ae95fa2783f837},
  intrahash = {5c9c83e89da2faa8906a5927fe7ca3ef},
  isbn = {1-59593-323-9},
  location = {Edinburgh, Scotland},
  pages = {625-632},
  publisher = {ACM Press},
  title = {Improved annotation of the blogosphere via autotagging and hierarchical clustering},
  url = {http://www.cs.usfca.edu/~brooks/papers/brooks-montanez-www06.pdf},
  year = 2006
}