Platforms for Digital Humanities

- Project Suspended Until Apr 20 due to Resource Availability

This Project will provide a Text Mining Service that will support and encourage those in the College of Arts, Humanities and Social Sciences to carry out large scale text mining on large volumes of texts which are currently licensed for use at the University of Edinburgh, but impossible to analyse at scale because of the barriers in place for non-computational researchers to access HPC facilities.

Text mining allows the large scale searching, and derivation of patterns and trends, in large volumes of text which would not be possible to be searched manually.

There is a large interest in CAHSS for assistance in mining historical newspapers (such as the British Library’s digital newspaper collection) and repositories of digitised texts (such as the 65,000 British Library’s 19th Century Texts, and the 68,000 Jisc Medical Heritage Library Texts), all of which we have the license to mine at Edinburgh.

In addition, establishing this service would allow volumes of scraped social network data and in-copyright material to be mined (with appropriate permissions). Analysis of such material will give insights into culture and society, while also investigating the best practice to do so (and there are opportunities for those in CAHSS to work closely with those in Informatics on more advanced analysis approaches, which will lead to new computer science research).