Outcomes

The AEOLIAN project will lead to the following outputs:

Six Workshops

1. “Employing Machine Learning and Artificial Intelligence in Cultural Institutions”
2. “Reimagining Industry / Academic / Cultural Heritage Partnerships in AI”
3. “What Challenges do Machine Learning and AI raise in terms of privacy, ethics, research integrity, reproducibility, and bias?”
4. “AI/ML: Increasing Access, Visibility, and Engagement”
5. “Making More Sense with Machines: AI/ ML Methods for interrogating and understanding our textual heritage in the Humanities, Natural Sciences, and Social Sciences ”
6. “New Horizons in AI and Machine Learning for Libraries and Archives”

Five Case Studies of US and UK Cultural Organisations

These case studies will feed into an open-access edited collection (under contract with UCL Press).

Two journal special issues
These two journal special issues will be based on research connected to the themes of the AEOLIAN project.

Special Issue 2 “Applying Innovative Technologies to Digitised and Born-Digital Archives”, ACM Journal on Computing and Cultural Heritage (JOCCH)

We invited contributions for a Special Issue on “Applying Innovative Technologies to Digitised and Born-Digital Archives” to be published in ACM Journal on Computing and Cultural Heritage (JOCCH).

This special issue brought together a range of disciplines (e.g. digital humanities, cultural heritage, archival studies, information studies, computer science), practices and sectors to explore the latest technologies being applied to digitised and born-digital archives across the globe. We particularly encouraged submissions from professionals in the GLAM sector (Galleries, Libraries, Archives and Museums).

Contents for Special Issue of ACM Journal on Computing and Cultural Heritage (Volume 16, Issue 4, 2023)

Introduction to the Special Issue “Applying Innovative Technologies to Digitised and Born-Digital Archives” – Lise Jaillant. Article No.: 74e, pp 1–3.

An Ontological Approach for Unlocking the Colonial Archive – Gustavo Candela, Javier Pereda, Dolores Sáez, Pilar Escobar, Alexander Sánchez, Andrés Villa Torres, Albert A Palacios, Kelly McDonough, Patricia Murrieta-Flores (Open Access). Article No.: 74, pp 1–18.

Positioning Paradata: A Conceptual Frame for AI Processual Documentation in Archives and Recordkeeping Contexts – Scott Cameron, Pat Franks, Babak Hamidzadeh. Article No.: 75, pp 1–19.

(Mis)matching Metadata: Improving Accessibility in Digital Visual Archives through the EyCon Project – Katherine Aske and Marina Giardinetti (Open Access). Article No.: 76, pp 1–20.

Optimization of Image Processing Algorithms for Character Recognition in Cultural Typewritten Documents – Mariana Dias, Carla Teixeira Lopes. Article No.: 77, pp 1–25.

Enriching Image Archives via Facial Recognition – Kenzo Milleville, Alec Van den Broeck, Nastasia Vanderperren, Rony Vissers, Matthias Priem, Nico Van de Weghe, Steven Verstockt. Article No.: 78, pp 1–18.

DoubleCheck: Designing Community-based Assessability for Historical Person Identification – Vikram Mohanty and Kurt Luther (Open Access). Article No.: 79, pp 1–27.

Annotations as Knowledge Practices in Image Archives: Application of Linked Open Usable Data and Machine Learning – Murielle Cornut, Julien Raemy, Florian Spiess (Open Access). Article No.: 80, pp 1–19.

Write What You Want: Applying Text-to-Video Retrieval to Audiovisual Archives – Yuchen Yang. Article No.: 81, pp 1–16.

Consolidating Research Data Management Infrastructure: Towards Sustainable Digital Scholarship – Megan Gooch, Damon Strange. Article No.: 82, pp 1–16.

Protecting Privacy in Digital Records: The Potential of Privacy Enhancing Technologies – Victoria Lemieux and John Werner. Article No.: 83, pp 1–18.

Probing Historical Image Contexts: Enhancing Visual Archive Retrieval through Computer Vision – Lin Du, Brandon Le, Edouardo Honig. Article No.: 84, pp 1–17.

On the Books: Jim Crow and Algorithms of Resistance, a Collections as Data Case Study – Amanda Henley, Lorin Bruckner, Hannah Jacobs, Matthew Jansen, Brianna Nunez, Rolando Rodriguez, Morgan Wilson. Article No.: 85, pp 1–20.

A Low-Cost Method and Surveying of the Historical Structures from Digital Resources – Sandeep Roy and Mriganka Basunia. Article No.: 86, pp 1–25.

Are Users of Digital Archives Ready for the AI Era? Obstacles to the Application of Computational Research Methods and New Opportunities – Lise Jaillant, Katherine Aske (Open Access). Article No.: 87, pp 1–16.

Semantic Solutions for Democratizing Archaeological and Numismatic Data Analysis – Eljas Oksanen, Frida Ehrnsten, Heikki Rantala, Eero Hyvönen (Open Access). Article No.: 88, pp 1–18.

Special Issue [1] “Artificial Intelligence for Cultural Heritage Materials”, Journal of Documentation

We invited contributions for a Special Issue on “Artificial Intelligence for Cultural Heritage Materials” to be published in Journal of Documentation (Emerald).

We were particularly enthusiastic to receive submissions from Digital Humanists, Computer Scientists, Cultural-Heritage Institutions, Archivists, Libraries and others who have a stake in born digital cultural heritage.

Contents for Special Issue of Journal of Documentation (Volume 80, Issue 5, 2024)

Guest editorial: Artificial Intelligence for Cultural Heritage Materials – Glen Layne-Worthey and J. Stephen Downie. pp 1025-1030.

Computer Vision and Machine Learning Approaches for Metadata Enrichment to Improve Searchability of Historical Newspaper Collections – Dilawar Ali, Kenzo Milleville, Steven Verstockt, Nico Van de Weghe, Sally Chambers, and Julie M. Birkholz. pp 1031-1056.

Automated Dewey Decimal Classification of Swedish Library Metadata Using Annif Software – Koraljka Golub, Osma Suominen, Ahmed Taiye Mohammed, Harriet Aagaard, and Olof Osterman.  pp 1056-1079.

Unsilencing Colonial Archives via Automated Entity Recognition – Mrinalini Luthra, Konstantin Todorov, Charles Jeurgens, and Giovanni Colavizza.  pp 1080-1105.

User Perspectives through Cross-Connections. The Role of Archives as Part of the German Digital Research Data Infrastructure – Kai Naumann and Andreas Neuburger. pp 1106-1118.

Datafication of Audiovisual Archives: From Practice Mapping to a Thinking Model – Yuchen Yang. pp 1119-1132.

Our Heritage, Our Stories: Developing AI tools to Link and Support Community-generated Digital Cultural Heritage – Ewan D. Hannaford, Viktor Schlegel, Rhiannon Lewis, Stefan Ramsden, Jenny Bunn, John Moore, Marc Alexander, Hannah Barker, Riza Batista-Navarro, Lorna Hughes, and Goran Nenadic.  pp 1133-1147.

Unlocking a Multimodal Archive of Southern Chinese Martial Arts through Embodied Cues – Yumeng Hou, Fadel Mamar Seydou, and Sarah Kenderdine. pp 1148-1166.

Validating predictions of burial mounds with field data: the promise and reality of machine learning – Adela Sobotkova, Ross Deans Kristensen-McLachlan, Orla Mallon, and Shawn Adrian Ross. pp 1167-1189.

Feature in ARC Magazine, Archives & Records Association (ARA)

Dr Katie Aske, Research Assistant for the AEOLIAN Network at Loughborough University, discusses the key outcomes of the network’s first workshop which addressed the ways in which Machine Learning and Artificial Intelligence can be leveraged to help organise, search and understand digital collections across the sector. See ‘Better Together: AEOLIAN Network’s First Workshop’, Feature in ARC Magazine, Issue 381, Archives & Records Association, pp. 25–27. ISSN: 2632-7171 (September to October 2021).

Digital Preservation Coalition (DPC) Blog Post

The first blog post, written by Paul Gooding, Senior Lecturer in Information Studies at the University of Glasgow, was published on the Digital Preservation Coalition (DPC) blog. A not-for-profit membership organization, the DPC was founded in 2002, and now gathers more than 100 agencies from 13 countries. The blog post introduces the AEOLIAN network and its project outputs. It also encourages readers to join our AEOLIAN list-serv to receive updates on our initiative and latest news.

Artificial Intelligence for Libraries, Archives & Museums (AI4LAM) Blog Post

The second blog post, published on the Artificial Intelligence for Libraries, Archives & Museums website, has been written by Glen Worthey, Associate Director for Research Support Services in the HathiTrust Research Center, based in the University of Illinois at Urbana-Champaign School of Information Sciences. Formed in 2018, AI4LAM is a collaborative framework for libraries, archives and museums to organize, share and elevate their knowledge about and use of artificial intelligence. This blog post details our partnerships and work so far, as well as our upcoming workshop on July 7. It also encourages readers to join our AEOLIAN list-serve to keep up to date with the project.

Archives Hub REVIEW: ‘Employing Machine Learning and Artificial Intelligence in Cultural Institutions Workshop’. 

Adrian Stevenson, Technical Innovations Manager of Digital Resources at Jisc reviews the first workshop from the AEOLIAN project for Archives Hub.

American Library Association’s Choose Privacy Every Day Blog Interview with Glen Worthey.

Virginia Dressler, Digital Projects Librarian at Kent State University interviews Glen Worthey in “Artificial Intelligence for Cultural Organizations (AEOLIAN) NEH Grant” for the American Library Association’s Choose Privacy Every Day blog.

News Eye interview: A Conversation with Dr Lise Jaillant.

Amanda Maunoury, National Library of France, interviews Lise Jaillant in “Artificial Intelligence for Cultural Organisations: A Conversation with Dr Lise Jaillant” for the News Eye blog.