@lee_peck

RSDC'08: Tag Recommendations using Bookmark Content

, , and . Proceedings of the ECML/PKDD 2008 Discovery Challenge Workshop, part of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, page 96--107. (2008)

Abstract

A variety of factors contribute to a tag being assigned by a user to adocument that he or she bookmarked. Textual information present in a URL's title,a user's description of a document, or a bibtex field associated with a scientificpublication are sources for automatically recommending tags relevant for a givenbookmark. Lymba's submission for the RSDC'08 Tag Recommendation task usesdocument and user models derived from the textual content associated with URLsand publications by social bookmarking tool users. This paper describes our naturallanguage understanding approach for producing tag recommendations andprovides some initial results of our internal evaluation.

Links and resources

Tags

community

  • @christine111
  • @lee_peck
@lee_peck's tags highlighted