Moving Beyond Text Digitization in Archives Using Both Human and Technological Resources

Abstract

In the past, the digitization of archival collections has focused on capture of and access to plain images of textual material. In the current cultural heritage environment, particularly with the shift of many archives workers and patrons to telework during the COVID-19 pandemic, an image of the archival object alone is not enough. Today archival collections need to be searchable and transcribable. This session discusses the power of both technological developments and more traditional humanistic "people power" to enhance digitized archival collections at scale. Come and hear how archives are crowdsourcing transcriptions of digitized texts, both through "volunpeers" from the public and teleworking staff, and using informatics tools for new methods of seeing and understanding collections such as OCR and artificial intelligence (AI).