The NEWSGAC (News Genres: Advancing Media History by Transparent Automatic Genre Classification) project, acquired by Laura Hollink and Jacco van Ossenbruggen, has kicked off last week week. Researchers of this project aim to open the 'black box' of machine learning in this joint project with the eScience Centre, the University of Groningen, the National Library of the Netherlands and the Netherlands Institute for Sound and Vision.
The researchers will develop metrics and guidelines to make bias and error of a wide range of machine learning approaches and preprocessing steps transparent. This will enable scholars in the humanities and social sciences to do large-scale data analyses, while at the same time critically evaluating the methodological effects of the use of machine learning. Starting on November 1, Aysenur Bilgin will strengthen the NEWSGAC team as a postdoc in the Information Access group.
The project will last to 31 December 2018 and is funded by CLARIAH (Common Lab Infrastructure for the Arts and Humanities.)
