Projects

Recognising Hands, Recognising Processes (Upcoming, Oct), National Library of Scotland, University of Sheffield. Internal Funding.

This project attempts to clarify the level of eXplainable AI needed for libraries to utilise digital transcription at scale. As memory institutions increasingly incorporate AI-enabled transcription into their collections systems, XAI offers a way to scrutinise outputs and model behaviour for non-technical users. Directed by libraries' growing emphasis on XAI, this project answers: what aspects of ATR need further explanation? How are developers positioning themselves toward XAI public-facing documentation? Can XAI increase library audiences’ trust in ATR resources? Does greater explainability compromise ATR performance?

Coming Soon

Using Handwritten Text Recognition (HTR) on The Life and Times of Frederick Douglass (1846-1894) (2024), University of Edinburgh, Library of Congress. AHRC.

Conducted while a Kluge Fellow, this project demonstrated the efficacy of text recognition - analysis pipelines on handwritten library collections, using the autobiographical works of Frederick Douglass (1818 - 1895) as a case study. The project aim was to understand how intimate histories contained in handwriting can challenge and develop cultural understandings previously reliant on mechanical printed text.

Making the Past Readable: The Impact of Handwritten Text Recognition on Libraries and Their Users (2020 - 2024). University of Edinburgh, Glasgow, National Library of Scotland, READ (Transkribus). AHRC.

This project considered the socio-technical infrastructure surrounding AI-enabled transcription of library collections. Despite sectoral awareness, institutional approaches still display gaps between conceptualising and operationalising HTR. Therefore, this project assess the impact of HTR on libraries, users, and the wider information environment? Such analysis resulted in a set of recommendations for HTR’s future provision, directed thematically at libraries, HTR users and developers.