BibSonomy :: bibtex  ::

tag user group author concept BibTeX key search:all search:dbenz_test
A blue social bookmark and publication sharing system.
tags · relations · groups · popular
help · blog · about
login · register
dbenz_test's BibTeX entry:  

Improved annotation of the blogosphere via autotagging and hierarchical clustering

WWW '06: Proceedings of the 15th international conference on World Wide Web, : 625--632, 2006.
Authors: Christopher H. Brooks and Nancy Montanez
URL: http://www2006.org/programme/item.php?id=583
Tags: automated_annotation blog closely_related clustering diploma_thesis tagging technorati
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.
| URL | BibTeX  
@inproceedings{brooks06-improved,
title = {Improved annotation of the blogosphere via autotagging and hierarchical clustering},
address = {New York, NY, USA},
author = {Christopher H. Brooks and Nancy Montanez},
booktitle = {WWW '06: Proceedings of the 15th international conference on World Wide Web},
pages = {625--632},
publisher = {ACM Press},
url = {http://www2006.org/programme/item.php?id=583},
year = {2006},
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.},
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}, ad_pdf = {http://www2006.org/programme/files/pdf/583.pdf}, lastdatemodified = {2006-07-18}, lastname = {Brooks}, own = {own}, pdf = {brooks06-improved.pdf}, read = {read},
keywords = {automated_annotation blog closely_related clustering diploma_thesis tagging technorati }
}