Inferring Semantic Facets of a Music Folksonomy with Wikipedia
|Title||Inferring Semantic Facets of a Music Folksonomy with Wikipedia|
|Publication Type||Journal Article|
|Year of Publication||In Press|
|Authors||Sordo, M., Gouyon F., Sarmento L., & Celma Ò.|
|Journal Title||Journal of Web Semantics|
|Short Title||Journal of Web Semantics|
|Keywords||Last.fm, Music tagging, Semantic categorization, Social music, Wikipedia|
Music folksonomies include both general and detailed descriptions of music,
and are usually continuously updated. These are signicant advantages
over music taxonomies, which tend to be incomplete and inconsistent among
them. However, music folksonomies have an inherent loose and open semantics,
which hampers their use in many applications, such as structured music
browsing and recommendation.
In this paper, we present a system that can (1) automatically obtain a
set of semantic facets underlying the folksonomy of the social music website
Last.fm, and (2) categorize Last.fm tags with respect to the obtained facets.
The semantic facets are anchored upon the structure of Wikipedia, a dynamic
repository of universal knowledge.
We evaluate both the relevance of the obtained facets by manually comparing
them with a compilation of facets from several expert-made music
taxonomies. We then evaluate the performance of the tag categorization
process by focusing on set of four gold-standard facets and comparing the
tags assigned by our system with the ones indicated by experts. Compared
to a WordNet baseline, our method increases by 144% the coverage of the
tags with a semantic assignment. Furthermore, our method is able to generate
several dozens of relevant facets, almost entirely reproducing the set
of gold-standard facets, while replicating many of the facet to tag associations.
Also, we illustrate the usefulness of the system in the particular task of
decomposing the tag description of music artists into the underlying facets.