Presentation on “Global Digital Humanities: Text Mining Multilingual Literary Corpora”

On January 24th, Mark Algee-Hewitt presented a new project: “Global Digital Humanities: Text Mining Multilingual Literary Corpora.”

Building on our collaborative, Mellon funded, History of “Literature”/Histoire de “littérature” project with CNRS in Paris (and drawing on our 8 additional active collaborations with other European Digital Humanities Centers), this project looks towards new ways of aligning the results of the quantitative analysis of literary phenomena across languages.

Although still in its early stages, our work seeks to establish a set of methods that will allow research on multi-lingual, or even global, literary phenomena without resorting to the inaccuracies of translation. This will not only allow Digital Humanities researchers to investigate multi-national literary phenomena, but will also help to redress the inequalities created by the over-representation of English language texts in quantitative literary study.