Despite progress on various technologies to support both digital preservation and description of archival materials, we have still seen relatively little progress on software support for the core activities of selection and appraisal. There are two considerations that make selection and appraisal of digital materials substantially different from selection and appraisal of analog materials: that digital materials exist at multiple levels of representation and that they are directly machine readable. There are great opportunities to better assist selection and appraisal of digital materials, including use of digital forensics tools, natural language processing, and machine learning.