The team, which includes Emeritus Professor Peter Ainsworth from the University of Sheffield´s Department of French and, Dr Michael Meredith from the University´s Humanities Research Institute, hopes that the tools and techniques developed during their 15-month project will revolutionise the ways in which people extract information from digital resources.
The Sheffield-Michigan-Illinois project will address three datasets: 15th-century illuminated manuscripts, 17th and 18th century maps, and 19th and 20th century quilts. Research questions to be explored include how visual and production styles of sources reflect regional tastes or historical moments, how traumatic historical events are manifested in cultural production, and how artefacts reflect and influence relationships between cultural groups.
The 'Digging into Data Challenge' competition is coordinated by four leading international research agencies: the Social Sciences and Humanities Research Council (SSHRC), of Canada; the National Endowment for the Humanities (NEH), of the United States; the National Science Foundation (NSF), of the United States; and the Joint Information Systems Committee (JISC), of the United Kingdom. The competition aims to promote innovative humanities and social science research using large-scale data analysis.
Just eight projects were chosen as winners from almost 150 applications. They will now go on to demonstrate how data mining (searching large-scale databases for patterns) and data analysis tools can improve research in the humanities and social sciences. It is anticipated that the more challenging data mining methodologies required for research in the humanities can then be applied across the sciences.
The Sheffield team will look at nine complete 15th century manuscripts of Froissart´s Chronicles digitised at high resolution and comprising approximately 6,100 images. The project will ask a number of questions, from where and by whom the manuscripts were created to how the manuscript reflects the tastes of the particular region and historical moment to which it belongs.
Professor Peter Ainsworth said: "This exciting project builds on productive relationships forged over several years with our American partners in art history and computer science, involving on-site and virtual seminars, and supported by small grants from the EPSRC, NSF, JISC/AHRC e-Science initiatives. We aim to use pattern recognition, data mining and other supercomputing techniques to bring fresh light to bear on areas of medieval scholarship that we believe can benefit significantly from the application of these new methodologies."
