A new publication with colleagues in Computer Science in Hypertext 2023. This project began from discussions between an art historian (me) and a computer scientists (Bernardo Pereira Nunes) about what we could do with large scale digital museum collections and what question an art historian wanted answered vs what innovations a computer scientist was interested in. With MA student Xinran Tian we investigated different ways to query and search the Met Collection (made available as a data set via their API) than the standard approach of most people who access them via the institutional website or find images via a Google Image search. This led on to discussion about bias – a topic of high importance for both humanities researchers and computer scientists, but one we approach from very different backgrounds. Hopefully this work can prompt more reflections on how we can design better systems that don’t try to hide bias, or pretend to fix bias that is the result of centuries of decision making (as at a major art museum) but find ways to be more transparent about its existence.
Abstract
Galleries, Libraries, Archives and Museums (GLAM) institutions are increasingly opening up their digitised collections and associated data for engagement online via their own websites/search engines and for reuse by third parties. Although bias in GLAM collections is inherent, bias in the search engines themselves can be rated. This work proposes a bias rating method to reflect on the use of search engines in the GLAM sector along with strategies to mitigate bias. The application of this to an existing large art collection shows the applicability of the proposed method and highlights a range of existing issues.
Read the full paper on ACM (or contact me for a version is you don;t have access) https://dl.acm.org/doi/10.1145/3603163.3609043
Leave a Reply