their-finest-hour-online-archive-c7cd9549·1 events·first seen Aliases: Their Finest Hour Online Archive
A research paper from arXiv evaluates three NLP approaches — Named Entity Recognition, Keyword Extraction, and Topic Modelling — for automating keyword assignment in crowdsourced digital collections, using the University of Oxford's Their Finest Hour Online Archive as a case study. The study spans traditional statistical methods through modern generative AI, finding that no single method is complete and that model choice substantially shapes results. Open-weight, extractive models are recommended for responsible deployment, while generative AI is flagged for accountability risks specific to crowdsourced metadata contexts. The paper also raises stewardship ethics around automated metadata generation when contributors are living participants.