AEOLIAN (Artificial intelligence for cultural organisations)

AEOLIAN（文化组织人工智能）

• 批准号: AH/V009443/1
• 负责人: Lise Jaillant
• 金额: $ 7.46万
• 依托单位: Loughborough University
• 依托单位国家: 英国
• 项目类别: Research Grant
• 财政年份: 2021
• 资助国家: 英国
• 起止时间: 2021 至 无数据
• 项目状态: 已结题
• 来源: https://gtr.ukri.org/projects?ref=AH%2FV009443%2F1
• 关键词: AEOLIAN; Artificial; intelligence; cultural; organisations

How can we unlock "dark" digital archives closed to the public? What is the role of Artificial Intelligence (AI) in making digitised and born-digital cultural records more accessible to users, on both sides of the Atlantic? AEOLIAN (Artificial intelligence for cultural organisations) focuses on born-digital and digitised collections that are currently closed to researchers and other users due to privacy concerns, copyright and other issues. Archives are meant to be used, not locked away. In order to unlock cultural assets, we need to work across disciplines and harness the latest technology. AEOLIAN brings together Digital Humanists, Computer Scientists, archivists and other stakeholders to transform the access and use of born-digital and digitised collections which are currently hidden away. Analysing vast amounts of data cannot be done manually: automation is no longer a choice, it is a necessity. Artificial Intelligence can be used to improve access to non-confidential materials through sensitivity review, for example by distinguishing between personal and business emails. AEOLIAN aims to unlock born-digital and digitised collections and open them up to a large number of users. Access to digital archives is essential, but we also need to anticipate the moment when born-digital records will be more accessible. To make sense of this mass of data, new methodologies are urgently needed, combining traditional methods in the humanities with data-rich approaches. Collaborations between humanities scholars, computer scientists, archivists and other stakeholders are therefore essential to make archives more accessible, but also to design new methodologies to analyse huge amounts of data.AI and machine learning create opportunities, but also challenges, for libraries, archives and museums. The project will address larger questions in the humanities - including ethical and social considerations at the centre of current debates on AI and digital technologies.The AEOLIAN project will lead to the following research outputs:_6 online workshops , which will result in the creation of an international network of theorists and practitioners working with born-digital and digitised archives. _5 case studies of US and UK cultural organisations . These case studies will feed into an open-access 100-page report for an interdisciplinary audience outlining avenues for future research._2 collections of essays published as special issue of journal or edited collection. The final report will offer a roadmap on born-digital and digitised cultural assets, based on 5 case studies of specific collections in the UK and US and detailed interviews. Crucially, it will also develop specific ideas for interdisciplinary research areas to solve the issue of access to digital cultural assets, which could form the basis of future research initiatives.Archives are of course not reserved to academic researchers. The online workshops and the website will foster public engagement on the topic of the changing nature of archival collections (from print to digital) in the twenty-first century.The website will keep track of all the project activities in the form of presentation materials from all workshop participants, video recordings of workshop presentations, and case studies that will then feed into the final report. Associated social media will help us connect with interested parties - in academia, archival institutions and beyond.

我们如何才能解锁对公众关闭的“黑暗”数字档案？人工智能（AI）在使大西洋两岸的用户更容易访问数字化和非数字化文化记录方面发挥了什么作用？AEOLIAN（文化组织的人工智能）专注于数字化和数字化收藏，由于隐私问题，版权和其他问题，目前对研究人员和其他用户关闭。档案是用来使用的，而不是锁起来的。为了释放文化资产，我们需要跨学科合作，利用最新技术。AEOLIAN汇集了数字人文主义者，计算机科学家，档案管理员和其他利益相关者，以改变目前隐藏的数字化和数字化收藏品的访问和使用。分析大量数据无法手动完成：自动化不再是一种选择，而是一种必需品。人工智能可用于通过敏感性审查来改善对非机密材料的访问，例如通过区分个人和商业电子邮件。AEOLIAN的目标是解锁数字化和数字化的收藏品，并向大量用户开放。获取数字档案是必不可少的，但我们也需要预测到非数字记录更容易获取的时刻。为了理解这些海量数据，迫切需要新的方法，将人文学科的传统方法与数据丰富的方法相结合。因此，人文学者、计算机科学家、档案管理员和其他利益相关者之间的合作对于提高档案的可访问性至关重要，同时也是设计分析大量数据的新方法的关键。人工智能和机器学习为图书馆、档案馆和博物馆创造了机遇，但也带来了挑战。AEOLIAN项目将解决人文领域的更大问题，包括当前人工智能和数字技术辩论的核心伦理和社会问题。AEOLIAN项目将产生以下研究成果：6个在线研讨会，这将导致创建一个国际网络的理论家和实践者与数字化和数字化档案工作。- -美国和英国文化组织的5个案例研究。这些案例研究将纳入一份开放获取的100页报告，为跨学科观众概述未来研究的途径。2篇论文集作为期刊特刊或编辑集出版。最终报告将根据对英国和美国特定藏品的5个案例研究以及详细的访谈，提供一个数字化和数字化文化资产的路线图。最重要的是，它还将为跨学科研究领域提出具体的想法，以解决数字文化资产的获取问题，这可能成为未来研究计划的基础。在线讲习班和网站将促进公众参与二十一世纪档案收藏性质的变化（从印刷到数字）这一主题，网站将以讲习班所有与会者的发言材料、讲习班发言录像和案例研究的形式跟踪所有项目活动，这些材料将纳入最后报告。相关的社交媒体将帮助我们与学术界、档案机构等感兴趣的各方建立联系。

项目成果

An Ontological Approach for Unlocking the Colonial Archive

• DOI: 10.1145/3594727
• 发表时间: 2023-04
• 期刊: ACM Journal on Computing and Cultural Heritage
• 影响因子: 2.4
• 作者: Gustavo Candela;J. Pereda;Dolores Sáez;Pilar Escobar;Alexander Sánchez;Andrés Villa Torres;Albert A. Palacios;Kelly S. Mcdonough;Patricia Murrieta-Flores

(Mis)Matching Metadata: Improving Accessibility in Digital Visual Archives through the EyCon Project

• DOI: 10.1145/3594726
• 发表时间: 2023-05
• 期刊: ACM Journal on Computing and Cultural Heritage
• 影响因子: 2.4
• 作者: Katherine Aske;Marina Giardinetti

Computer vision and machine learning approaches for metadata enrichment to improve searchability of historical newspaper collections

• DOI: 10.1108/jd-01-2022-0029
• 发表时间: 2023-02
• 期刊: Journal of Documentation
• 影响因子: 2.1
• 作者: Dilawar Ali;Kenzo Milleville;S. Verstockt;N. van de Weghe;Sally Chambers;Julie M. Birkholz

The Library Catalogue as Dataset: Exploring Data Science Approaches to Analyse Collections at Scale

图书馆目录作为数据集：探索大规模分析馆藏的数据科学方法

• 发表时间: 2022
• 作者: Havens L

Positioning Paradata: A Conceptual Frame for AI Processual Documentation in Archives and Recordkeeping Contexts

定位 Paradata：档案和记录保存环境中人工智能流程文档的概念框架

• DOI: 10.1145/3594728
• 发表时间: 2023
• 期刊: Journal on Computing and Cultural Heritage
• 作者: Cameron S