]> 2026-05-29T15:49:22+00:00 Workflow:Appraise email and other large, unstructured text collections 3000 en-gb The workflow is intended for use with email collections in PST format, but it can be adapted to support most other email formats as well as most common office productivity formats including PDF and Word. Appraise email and other large, unstructured text collections University of Illinois The outputs include deduplicated & reformatted (PST->EML) files, over 100 extracted metadata attributes about each document, extracted attachments, indexing (OCR & audio transcriptions), plain text versions, and scores indicating if the document is archival and/or sensitive (with accompanying statistics). Experimental 2024-02-06T18:57:51Z 2460347.2901736 Appraise email and other large, unstructured text collections