International Research Collaboration Network in Computational Archival Science (IRCN-CAS)

点击翻译按钮获取中文摘要

The large-scale digitisation of analogue archives, the emerging diverse forms of born-digital archive, and the new ways in which researchers across disciplines (as well as the public) wish to engage with archival material, are disrupting traditional archival theories and practices, and are presenting challenges for practitioners and researchers who work with archival material. They also offer enhanced possibilities for scholarship, through the application of computational methods and tools to the archival problem space, and, more fundamentally, through the integration of 'computational thinking' with 'archival thinking'. This potential has led the collaborators in this proposal to identify Computational Archival Science (CAS) as a new field of study (see http://dcicblog.umd.edu/cas/).This Network will extend this prior work by engaging directly with the archive community and archival practitioners. The specific research focus of the Network will be on the use of computational methods for contextualising digital records, both digitised and born-digital. Contextualisation is one of the central challenges for the modern archive highlighted in the Digital Strategy 2017-19 from The National Archives, and is an area in which computational methods have great potential. The Network will reach out directly to archives and archival practitioners, establishing systematic collaborations and research programmes that leverage and extend the innovative research being carried out within individual institutions in this area. The context of a record is key for understanding its value as historical evidence, and the ability to map out and provide access to that context is key for conferring value on what would otherwise be (relatively) disconnected pieces of information, enabling them to be used effectively - found, understood and re-purposed - by historians and other archive-centric scholars drawing on the archival evidence base. The increasingly digital nature of the archive provides opportunities as well as challenges for addressing this question, by using a range of computational methods for meeting the increasingly complex demands of both archival users and practitioners. This Network will organise a series of interconnected events to explore this question of contextualisation, whether through capturing metadata, enhancing records by semantic tagging, or indeed contextualising records with other records, and thus connecting up previously disconnected information into 'knowledge graphs'. We will not focus on specific technologies, but rather examine a range of technologies with potential for meeting this challenge, including natural language processing, graph technologies, machine learning, probabilistic approaches, and other methods from the broad field of data science and AI. The focus will thus be on the research question rather than the technology.The events will be organised as two research symposia and two 'datathons'. The first symposium will be a participatory event focusing on identifying and opening up the questions we will explore, with participants from the complementary fields of information/archival science, computer/data science, and archival practice. The datathons will conduct hands-on experiments relating to some of these questions, through small teams of researchers - with a particular focus on early career researchers and graduate students - who will work collaboratively on small projects applying computational methods to a range of challenges relating to record contextualisation. One datathon will focus on digitised records, the other on born-digital records. The closing symposium will then draw these threads together, focusing on reflection, synthesis, and identifying future programme of work and collaborations, with a view to implementing some of the ideas generated in practice. We will produce a final white paper that integrates the Network's conclusions and recommendations for further work.