Towards the Semantic Web: Collaborative Tag Suggestions

@inproceedings{Xu2006, abstract = {Content organization over the Internet went through several interesting phases of evolution: from structured directories to unstructured Web search engines and more recently, to tagging as a way for aggregating information, a step towards the semantic web vision. Tagging allows ranking and data organization to directly utilize inputs from end users, enabling machine processing of Web content. Since tags are created by individual users in a free form, one important problem facing tagging is to identify most appropriate tags, while eliminating noise and spam. For this purpose, we define a set of general criteria for a good tagging system. These criteria include high coverage of multiple facets to ensure good recall, least effort to reduce the cost involved in browsing, and high popularity to ensure tag quality. We propose a collaborative tag suggestion algorithm using these criteria to spot high-quality tags. The proposed algorithm employs a goodness measure for tags derived from collective user authorities to combat spam. The goodness measure is iteratively adjusted by a reward-penalty algorithm, which also incorporates other sources of tags, e.g., content-based auto-generated tags. Our experiments based on My Web 2.0 show that the algorithm is effective.}, address = {Edinburgh, Scotland}, author = {Xu, Zhichen and Fu, Yun and Mao, Jianchang and Su, Difu }, booktitle = {Proceedings of the Collaborative Web Tagging Workshop at the WWW 2006}, citeulike-article-id = {1037682}, keywords = {classification, collaboration, collaborative, cooperative, folksonomy, social, tagging}, posted-at = {2007-05-24 20:51:55}, priority = {4}, title = {Towards the Semantic Web: Collaborative Tag Suggestions}, url = {http://www.ibiblio.org/www\_tagging/2006/13.pdf}, year = {2006} }

TY - CONF ID - Xu2006 L3 - citeulike-article-id:1037682 TI - Towards the Semantic Web: Collaborative Tag Suggestions T2 - Proceedings of the Collaborative Web Tagging Workshop at the WWW 2006 AD - Edinburgh, Scotland N2 - Content organization over the Internet went through several interesting phases of evolution: from structured directories to unstructured Web search engines and more recently, to tagging as a way for aggregating information, a step towards the semantic web vision. Tagging allows ranking and data organization to directly utilize inputs from end users, enabling machine processing of Web content. Since tags are created by individual users in a free form, one important problem facing tagging is to identify most appropriate tags, while eliminating noise and spam. For this purpose, we define a set of general criteria for a good tagging system. These criteria include high coverage of multiple facets to ensure good recall, least effort to reduce the cost involved in browsing, and high popularity to ensure tag quality. We propose a collaborative tag suggestion algorithm using these criteria to spot high-quality tags. The proposed algorithm employs a goodness measure for tags derived from collective user authorities to combat spam. The goodness measure is iteratively adjusted by a reward-penalty algorithm, which also incorporates other sources of tags, e.g., content-based auto-generated tags. Our experiments based on My Web 2.0 show that the algorithm is effective. KW - classification KW - collaboration KW - collaborative KW - cooperative KW - folksonomy KW - social KW - tagging AU - Xu, Zhichen AU - Fu, Yun AU - Mao, Jianchang AU - Su, Difu PY - 2006/// UR - http://www.ibiblio.org/www_tagging/2006/13.pdf ER -