Tag Clustering with Self Organizing Maps
Sbodio, Marco Luca; Simpson, Edwin
Keyword(s): SOM, clustering, machine learning, folksonomy, tagging, web 2.0
Abstract: Today, user-generated tags are a common way of navigating and organizing collections of resources. However, their value is limited by a lack of explicit semantics and differing use of tags between users. Clustering techniques that find groups of related tags could help to address these problems. In this paper, we show that a Self-Organizing Map (SOM) can be used to cluster tagged bookmarks. We present and test an iterative method for determining the optimal number of clusters. Finally, we show how the SOM can be used to intuitively classify new bookmarks into a set of clusters.
External Posting Date: October 6, 2009 [Fulltext]. Approved for External Publication
Internal Posting Date: October 6, 2009 [Fulltext]