Armadillo: Historical Data Mining

Summary:

This project used a set of online resources in 18th century British social history to evaluate the potential benefits of Semantic Web technology for Arts and Humanities researchers.

Project Status:

Completed

Funders:

Arts and Humanities Research Council (AHRC)

Partners:

University of Sheffield
University of Hertfordshire

Subjects:

social history, software development, text and image analysis, text data mining

Technologies:

Natural Language Processing

Project Website

Project Description

This project used a set of online resources in eighteenth-century British social history to evaluate the potential benefits of Semantic Web technology for Arts and Humanities researchers. Online materials of the greatest potential value to scholars, such as library archives and digitised collections, were facing growing problems of redundancy and irrelevance. Traditional searching methods, such as keyword searching, produced multiple versions of the same information or information whose context, when investigated manually, made it irrelevant to the research question being pursued.

At the University Of Sheffield, the Natural Language Processing Group has been at the forefront of technologies to cope with the huge challenges of modern knowledge management. The major output from this work was the development of Armadillo, a tool designed to provide machine readable content for the Semantic Web. The ways in which the Armadillo technology might benefit the Humanities Computing field were evaluated.

Duration: July 2005 – June 2007

Project Team

  • Prof. Mark Greengrass (Department of History, University of Sheffield)
  • Prof. Tim Hitchcock (Social Sciences, Arts and Humanities Research Institute, University of Hertfordshire)
  • Prof. Fabio Ciravegna (Department of Computer Science, University of Sheffield)
  • Jamie McLaughlin (Digital Humanities Developer – University of Sheffield)