Looking Beyond Genres: Identifying Meaningful Semantic Layers from Tags in Online Music Collections

A scheme for identifying the semantic layers of music-related tags is presented. Arguments are provided why the applications of the tags cannot be effectively pursued without a reasonable understanding of their semantic qualities. The identification scheme consists of a set of filters. The first is related with social consensus, user-count ratio, and n-gram properties of tags. The next relies on look-up functions across multiple databases to determine the probable semantic layer of each tag. Examples of the semantic layers with prevalence rates are given based on application of the scheme to a subset of the Million Song Dataset. Finally, a validation of the results was carried out with an independent, smaller hand-annotated dataset, in which high agreement between the identification provided by the scheme and annotations was found.

[1]  Roelof van Zwol,et al.  Classifying tags using open content resources , 2009, WSDM '09.

[2]  Peter Broeder,et al.  Models of Language Acquisition: Inductive and Deductive Approaches , 2001 .

[3]  Jeffrey Mark Siskind,et al.  Learning Word-to-Meaning Mappings , 1997 .

[4]  Joan Serrà,et al.  Music Mood Representations from Social Tags , 2009, ISMIR.

[5]  Wolfgang Nejdl,et al.  Improving music genre classification using collaborative tagging data , 2009, WSDM '09.

[6]  K. Scherer,et al.  Emotions evoked by the sound of music: characterization, classification, and measurement. , 2008, Emotion.

[7]  J.A.A. Simons.  Tag-elese or The Language of Tags , 2008 .

[8]  Dunja Mladenic,et al.  Automatic Evaluation of Ontologies , 2007 .

[9]  P. Laukka,et al.  Expression, Perception, and Induction of Musical Emotions: A Review and a Questionnaire Study of Everyday Listening , 2004 .

[10]  Christiane Fellbaum,et al.  Book Reviews: WordNet: An Electronic Lexical Database , 1999, CL.

[11]  Thierry Bertin-Mahieux,et al.  Autotagger: A Model for Predicting Social Tags from Acoustic Features on Large Music Databases , 2008 .

[12]  Thierry Bertin-Mahieux,et al.  The Million Song Dataset , 2011, ISMIR.

[13]  Paul Lamere,et al.  Social Tagging and Music Information Retrieval , 2008 .

[14]  W. Batchelder,et al.  Culture as Consensus: A Theory of Culture and Informant Accuracy , 1986 .

[15]  Eric Brill,et al.  A Simple Rule-Based Part of Speech Tagger , 1992, HLT.

[16]  Mark B. Sandler,et al.  Music Information Retrieval Using Social Tags and Audio , 2009, IEEE Transactions on Multimedia.

[17]  Justin Donaldson,et al.  Uncovering Affinity of Artists to Multiple Genres from Social Behaviour Data , 2008, ISMIR.

[18]  Jennifer C. Lena,et al.  Classification as Culture: Types and Trajectories of Music Genres , 2008 .

[19]  Valentin Robu,et al.  The complex dynamics of collaborative tagging , 2007, WWW '07.

[20]  S. Weller.  Cultural Consensus Theory: Applications and Frequently Asked Questions , 2007 .

[21]  Tuomas Eerola,et al.  Timbral Qualities of Semantic Structures of Music , 2010, ISMIR.