Natural Language Processing and Machine Learning as Practical Toolsets for Archival Processing

View/ Open
Date
2020-05-16Author
Hutchinson, Tim
Publisher
Emerald Publishing LimitedType
ArticlePeer Reviewed Status
Peer ReviewedMetadata
Show full item recordAbstract
Purpose – This study aims to provide an overview of recent efforts relating to natural language processing (NLP) and machine learning applied to archival processing, particularly appraisal and sensitivity reviews, and propose functional requirements and workflow considerations for transitioning from experimental to operational use of these tools.
Design/methodology/approach – The paper has four main sections. 1) A short overview of the NLP and machine learning concepts referenced in the paper. 2) A review of the literature reporting on NLP and machine learning applied to archival processes. 3) An overview and commentary on key existing and developing tools that use NLP or machine learning techniques for archives. 4) This review and analysis will inform a discussion of functional requirements and workflow considerations for NLP and machine learning tools for archival processing.
Findings – Applications for processing e-mail have received the most attention so far, although most initiatives have been experimental or project based. It now seems feasible to branch out to develop more generalized tools for born-digital, unstructured records. Effective NLP and machine learning tools for archival processing should be usable, interoperable, flexible, iterative and configurable.
Originality/value – Most implementations of NLP for archives have been experimental or project based. The main exception that has moved into production is ePADD, which includes robust NLP features through its named entity recognition module. This paper takes a broader view, assessing the prospects and possible directions for integrating NLP tools and techniques into archival workflows.
Citation
Hutchinson, Tim (2020). Natural language processing and machine learning as practical toolsets for archival processing. Records Management Journal, 30(2), 155-174. https://doi.org/10.1108/RMJ-09-2019-0055Subject
Archival appraisal
Machine learning
Computational archival science
Natural language processing (NLP)
Personally identifiable information (PII)
Sensitivity review
Collections
The following license files are associated with this item: