Inproceedings,

Mining the Structure of Tag Spaces for User Modeling

, , , and .
Proceedings of the UM 2007 workshop on Data Mining for User Modeling (DMUM07), page 30--31. Corfu, Greece, (June 2007)Extended abstract.

Abstract

We propose an approach for using data from a social tagging application like del.icio.us as a basis for user adaptation. We discuss several algorithms for mining taxonomies of tags from tag spaces. The mined taxonomy can be used to define adaptation rules that determine how to adapt a system to a user given the user's personal tag space. The contributions of this work are a description of an application scenario for taxonomy-mining algorithms, a discussion of algorithms by Mika3, Heymann et al.2, and Schmitz et al.4, and the proposal of an extension to the algorithms that takes the contexts of tags into account when building a taxonomy. We look at the performances of the algorithms on a dataset retrieved from del.icio.us and give a tentative recommendation of what algorithm to use.

Tags

Users

  • @kweiand

Comments and Reviews