Practical Linked Data for MIR Researchers

An ISMIR 2011 tutorial, 24th October 2011 (afternoon)
Miami, Florida, USA

Presenters:

Kevin Page and David De Roure
Oxford e-Research Centre, University of Oxford, UK
kevin.page@oerc.ox.ac.uk, david.deroure@oerc.ox.ac.uk

Tutorial slides

The tutorial slides are available here as PDF.

Tutorial Hands-on session notes

The notes for the hands-on parts of the tutorial can be found here.

Introduction

Research disciplines from the sciences to arts and humanities are experiencing a change in practice in order to benefit from the wealth of data now available in digital form. This shift to an increasingly data-intensive research method, described in science as the fourth paradigm, is enabled by the new computational tools and techniques that characterise e-Science and e-Research. Developments in Music Information Retrieval (MIR) reflect this phenomena, with the increased focus on ever larger quantities of information seen in a number of projects and shared datasets such as the SALAMI project (Structural Analysis of Large Amounts of Music Information) and the Million Song Dataset.

For MIR, the availability of larger datasets not only raises many potential research questions though the comparison and combination of large quantities of MIR algorithmic output, but also the possibility of enhancements throughout the research lifecycle: more sophisticated and adaptable approaches to creating and managing distributed signal collections, and the opportunity to produce new and novel findings by relating algorithmic output to non-MIR data from within and without the music domain.

Linked Data is an approach that combines structured semantics with the large-scale distributed architecture proven through the World Wide Web, and is proving to be an approach with great potential that has generated significant interest in the MIR and the wider music community (borne out by several papers and demonstrations at previous ISMIR conferences, and music-related submissions at conferences such as ISWC). It is a means by which we can use, publish, enhance, and most importantly link between the growing number of de-centralised information sources in the web of data, so as to develop new MIR systems that are improved by their access to these datasets, and which increase their utility by making results more readily consumable and linkable to the rest of the Semantic Web.

Presenter Biographies

David De Roure is Professor of e-Research in the Oxford e-Research Centre where he has particular responsibility for research in Digital Humanities including computational musicology. He has extensive teaching experience including an industrial course in Service Oriented Architectures and summer schools in distributed computing and in Web Science. Closely involved in the UK e-Science programme, his research projects draw on Web 2.0, Semantic Web, scientific workflow and pervasive computing technologies. He focuses on the co-evolution of digital technologies and research methods in and between multiple disciplines including digital social research, chemistry, bioinformmatics and environmental science. He has an extensive background in Web and Linked Data, runs the myExperiment.org social website and is a Web Science champion for the Web Science Trust.

Kevin Page is a researcher in the Oxford e-Research Centre, University of Oxford, UK. His work on web architecture and the semantic annotation and distribution of data has, through participation in several UK, EU, and international projects, been applied across a wide variety of domains including sensor networks, music information retrieval, clinical healthcare, and remote collaboration for space exploration. He has previously undertaken undergraduate lecturing, demonstrating, and supervision, and led and delivered Further Education courses in programming. He was co-presenter of the upcoming tutorial "Building Semantic Sensor Webs and Applications" at the 2011 Extended Semantic Web Conference.