Growing our TEXT MINING capacity
As part of our second Text Mining Lab in the summer of 2021, we supported six researchers to develop questions based on their interests, and then to use defoe to run queries against a variety of datasets. An exciting range of research questions emerged, ranging from testing conformity of company constitutional documents, to how the economy has been framed in newspaper discourse, to shifts in public perception of Kashmir, to the reception of Latin poetry in British publications. Researchers were supported in exploring these questions by our colleagues at the Edinburgh Parallel Computing Centre. This year we have also been trialling the use of ProQuest's TDM Studio, a workspace in which researchers have been able to explore and analyse ProQuest data.
We're also thrilled to have recruited a new team member this year: Dr Jessica Witte will take up an EFI Postdoctoral Fellowship in Text Mining in June and, alongside her own project, she has a remit to work with CDCS to help others get started with these exciting methods. To complement this support, we've also been looking at how we can increase the range of materials that researchers in the arts and humanities can access for computational analysis. We've purchased a large set of newspaper data from ProQuest, including titles from Britain and the United States published over the course of the Nineteenth and early Twentieth Centuries. We've also sponsored digitisation of more of the University's collections in partnership with colleagues in Library and University Collections. Together we're aiming to build up an impressive collection of historical digitised materials which could underpin a huge range of research topics.
