DISKAH Fellowship Award for Newspaper Data Project

We're delighted to announce that Dr Jessica Witte, CDCS Digital Research Analyst, has been awarded a fellowship from the Digital Skills in the Arts & Humanities (DISKAH) Network to support her work to improve access to digitised historical newspaper collections. During the one-year fellowship, Jessica will develop and trial a new workflow using fine-tuned large language models (LLMs) to address complex optical character recognition (OCR) errors in the digitised archive of The Scotsman newspaper. The outcome will include openly available tools, documentation, and guidance to support others working with similarly challenging historical materials.

Although the University of Edinburgh holds the license for The Scotsman archive—along with a range of other newspaper titles—high error rates in the digitised collections preclude searchability and analysis of the collections. Jessica’s work aims to make this archive more accessible for research and teaching through a scalable, user-friendly pipeline.

The DISKAH Network builds capacity for working with digital research infrastructure such as high-performance computing (HPC) in the arts and humanities. You can learn more about DISKAH and the fellowship scheme here.