A computational model of canonicity based on a diachronic digital corpus of canonical and non-canonical Dutch novels 1800-2000

Dr Andreas van Cranenburgh was a researcher-in-residence at the KB in 2021.

In his project 'A computational model of canonicity based on a diachronic digital corpus of canonical and non-canonical Dutch novels 1800-2000', he explored the question: how predictable is canonicity in texts?

Blogposts

A dataset of Dutch Novels 1800-2000

Dr Andreas van Cranenburgh

24 Jan 2022

Machine learning canonicity in Dutch novels 1800-2000

Dr Andreas van Cranenburgh

24 Jan 2022

Tools/Datasets

Dutch Novels 1800-2000

Dataset that contains a corpus of 1346 novels from DBNL.

Canonizer

The Canonizer demonstrates how well canonicity can be classified based on the text of a novel.

Andreas van Cranenburgh

Assistant professor Digital Humanities and Information Sciences

Personal Github page with list of publications

Personal page University of Groningen

Dutch novels 1800-2000 [dataset]

Canonizer

A dataset of Dutch Novels 1800-2000 [part 1]

Machine learning canonicity in Dutch novels 1800-2000 [part 2]

BIO

Andreas van Cranenburgh is assistant professor Digital Humanities and Information Science at the University of Groningen. He works on natural language processing with applications on literary studies.