Improved annotation of the blogosphere via autotagging and hierarchical clustering Export

@inproceedings{citeulike:761569, abstract = {Tags have recently become popular as a means of annotating and organizingWeb 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}, citeulike-article-id = {761569}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1135777.1135869}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/1135777.1135869}, doi = {10.1145/1135777.1135869}, isbn = {1-59593-323-9}, keywords = {cs541}, location = {Edinburgh, Scotland}, pages = {625--632}, posted-at = {2009-04-07 05:08:11}, priority = {2}, publisher = {ACM}, title = {Improved annotation of the blogosphere via autotagging and hierarchical clustering}, url = {http://dx.doi.org/10.1145/1135777.1135869}, year = {2006} }

TY - CONF ID - citeulike:761569 L3 - citeulike-article-id:761569 N2 - Tags have recently become popular as a means of annotating and organizingWeb 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. CY - Edinburgh, Scotland SN - 1-59593-323-9 AD - New York, NY, USA EP - 632 TI - Improved annotation of the blogosphere via autotagging and hierarchical clustering PB - ACM T2 - WWW '06: Proceedings of the 15th international conference on World Wide Web SP - 625 KW - cs541 AU - Brooks, Christopher AU - Montanez, Nancy PY - 2006/// UR - http://dx.doi.org/10.1145/1135777.1135869 ER -