210902 Text Mining: Comparing Parliaments, Novels, and Newspapers
From Jon Svensson
Comparing Parliaments, Novels, and Newspapers
We live in a time of massive and available datasets such as parliamentary records, novels, and newspaper collections. It is truly a great time to be a researcher of literature, politics, and media–– and to perform interdisciplinary scholarly work.
What happens when we start to ask how similar events are treated in different types of publishing, for example in parliamentary debates, newspapers, and novels? How do ideas, themes and concepts travel across different text genres? And how do the meaning of ideas, themes and concepts change when they travel across different text genres? What obstacles are there to measure such transmission? And what are the best statistical devices for exploring causality, influence, and allusion across databases? These and similar questions will be discussed at the seminar.
The seminar brings together a group of scholars with experiences of working with various textual corpora. At the seminar, the participants will present ongoing work on comparing different collections, and afterwards engage in a moderated panel discussion.
Moderator: Jo Guldi (Southern Methodist University)
Ruth Ahnert & Daniel Wilson (Queen Mary University of London, and The Alan Turing Institute): "Tracing the language of machines across genres: books, journals and newspapers"
Mark Algee-Hewitt (Stanford University): "Re-Formations: The Semantic Spaces of Revolution in the Long Eighteenth-century"
Lesley Jefferies & Brian Walker (University of Huddersfield): "Keywords and comparative studies of genres: political print news reporting and Hansard"
Ludovic Rheault (University of Toronto): "Using methods of natural language processing across domains and genres: Insights from research on parliamentary debates"