Archives

<p>The <em>LGBTQ+ AV Archive Mining Project</em> (2020-2021) was aimed at developing and making available models for extracting text, building usable text datasets, and developing public-facing data visualizations based on audiovisual (AV) materials in the LGBTQ+ collections in the <a href="https://uwm.edu/libraries/archives/">UWM Archives</a>. The <em>LGBTQ+ AV Archive Mining Project</em> used machine learning tools and human quality control and oversight to build and process the text datasets available here. <p><p>Creation of this corpus was funded by the Andrew W. Mellon Foundation as part of the second cohort for <a href="https://collectionsasdata.github.io/part2whole/">Collections as Data: Part to Whole</a>.</p>