Tasks: Search & Retrieval; Digitisation; Appraisal; Archival Aggregations (Arrangement); and Automated Metadata Generation (Description).
AI search tools offer:
Semantic search (understands user intent)
Personalised results based on search history
Example: Ask “Unisa student protests in the 1980s” and find exact results (ChatGPT)
Copilot: Type 'How do I access the Unisa Archives?'; 'What types of materials are in the archives?'.
AI can assist in digitising archival materials, making them more accessible. AI-powered Optical Character Recognition (OCR) software can be used to convert scanned images of text into machine-readable text. This is particularly useful for digitising manuscripts. ChatGPT Vision can be the example that can be practicable https://youtu.be/tHF8bwVJ--4?si=1E9xd72QGMew8c-Y
The other AI tool that can be used for digitisation of archival materials can be Transkribus AI. It is an AI platform that supports archival records. Transkribus AI enables the automatically text recognition, layout, and structure of the records and it can be trained by models that fit archival needs. Transkribus is an AI-powered platform for text recognition, transcription and searching of archival records. It can be viewed on the link below: Scanning
The process of evaluating records to determine their value for long-term preservation.
AI Capabilities:
Machine learning algorithms can analyse large volumes of data to identify valuable records based on historical trends and user-defined criteria.
AI-driven predictive analytics to assess future value and relevance.
Benefits:
Improved decision-making and resource allocation in archival storage.
Organizing and structuring records in a logical order for easy access and retrieval.
AI Capabilities:
AI can automate classification and clustering of records based on content analysis.
Natural language processing (NLP) can group related records, making arrangement more intuitive.
Benefits:
Faster, more consistent arrangement of archives, improving access and usability.
Creating descriptive information about archival records to improve discoverability.
AI Capabilities:
NLP and machine learning can generate metadata based on content analysis, titles, and keywords.
Computer vision can add metadata for visual records by recognising objects and text within images.
Benefits:
Reduces manual work and ensures consistent, comprehensive metadata for better searchability.