Abstract:”This paper examines the use of two kinds of context to improve the results of content-based music taggers: the relationships between tags and between the clips of songs that are tagged. We show that users agree more on tags applied to clips temporally “closer” to one another; that conditional restricted Boltzmann machine models of tags can more accurately predict related tags when they take context into account; and that when training data is “smoothed” using context, support vector machines can better rank these clips according to the original, unsmoothed tags and do this more accurately than three standard multi-label classifiers. “
New paper in ACM Transactions
More from PublicationsMore posts in Publications »
- “Measuring scientific brain drain with hubs and authorities: A dual perspective” is out!
- “Developing Real Estate Automated Valuation Models by Learning from Heterogeneous Data Sources” is out!“Developing Real Estate Automated Valuation Models by Learning from Heterogeneous Data Sources” is out!
- “PyPlutchik: Visualising and comparing emotion-annotated corpora” is out!
- Our study on “Immigration as a Divisive Topic” is out on Future Internet
- The emergence of structural inequalities from a nation-wide wire transfers network