Our major output is a new online resource, freely available to all, providing provide users with access to the ‘Linguistic DNA’ of Early Modern printed discourse, now available for beta-testing.

Users can:

  • configure and explore visualisations of the lexical structure of early English print as a whole and in time, author and genre-led slices;
  • see how discursive associations are dispersed across texts and how their strength changes through time;
  • locate items related to a pre-existing field of interest through a range of user-led search options; and
  • view every single word within the context of its original text.

The above features are currently being refined, and will soon be joined by additional features:

  • Discover relationships between discursive concepts and the classical ontology of the Historical Thesaurus, using the work of LDNA’s Lexical Pressure team at the University of Glasgow.
  • Visualise the discursive components of different genres with added collections based on TCP metadata.

Interested programmers will also be able to view the code on GitHub and plan their own customised implementations.

In related work, our team has already applied concept-modelling approaches to inform research into social media discourse (see Militarization 2.0) and support a major literature review in the Social Sciences (Ways of Being in a Digital Age). We anticipate further applications in public and corporate domains, providing insight into historic and contemporary discourse, and identifying trends, behaviour and demographic change.

In future, Linguistic DNA data and methods should underpin research projects on the linguistic and epistemological structures of modern knowledge.  At an impact workshop in June 2018, we discussed opportunities and applications including the next generation of semantic search engines, and finetuning discovery services for archives and publishers to automatically classify and relate materials. We welcome enquiries from all sectors.