Cal Lee (Professor at the School of Information and Library Science at the University of North Carolina, Chapel Hill) spoke at the second Unlocking our Digital Past workshop on 16 September 2021. Cal’s talk focused on the ways in which Natural Language Processing and other Machine Learning tools can be incorporated into archival appraisal and selection workflows.
The abstract for Cal’s talk read as: “One can encounter digital materials at numerous levels of representation, ranging from raw bitstreams read from physical media to high-level aggregations of digital objects. Selection and appraisal of born-digital materials are iterative processes, with each representation level revealing information that can inform professional judgements. This presentation will discuss several open-source software projects that have incorporated natural language processing and machine learning into selection and appraisal workflows.”
You can view Cal’s presentation below.