The final publication in the conference proceedings is available here: https://link.springer.com/chapter/10.1007/978-3-031-21756-2_41
In its final month, DISTILL work in collaboration with GATE Institute, and the Institute of Mathematics and Informatics of the Bulgarian Academy of Sciences was presented at one of the key international conferences in the digital domain, ICADL 2022. The 24th edition of the International Conference on Asian Digital Libraries, ICADL 2022 was hosted this year in Hanoi, Vietnam, from November 30 – December 2, 2022. Its main topic was “From Born-Physical to Born-Virtual: Augmenting Intelligence in Digital Libraries”.
Looking at emerging areas of innovation as one of the pillars of augmenting intelligence in digital libraries, DISTILL focused some of its effort on the emerging new ecosystems for digital cultural heritage, the Common European Data Space for Cultural Heritage, an effort spearheaded by Europeana Foundation.
To make a strong and compelling entry into the GLAM world, this new ecosystem needs to offer clear use cases which demonstrate that the data space allows for achieving results which were not viable within the existing infrastructures.
Our paper looked at the needs of users as captured by several recent studies. It shows that there is no consensus and a widely accepted model of user needs within the digital cultural heritage domain. However, the paper argues that the experience accumulated within GLAM Labs can provide inspirational use cases which can scale up from the single institution setting to the data space.
Some of the previous individual research projects delivered within the BL Labs used advanced tools for image analysis. Back in 2016, a project called “Nineteenth-century Newspaper Analytics“, by Paul Fyfe and Qian Ge was a runner up for the BL Labs research award. It explored “how can computer
vision and image processing techniques be adapted for large-scale interpretation of historical illustrations?” While here the focus was on exploring a specific set of digitised newspapers from the collection of the British Library, it is easy to imagine a use case which would take image identification, analysis and enriching metadata combining descriptions from different institutions in a data space use case.
Here is a use case which can be implemented with the common European data space. Imagine that an archivist (or even a citizen with a personal archive) has a historical photograph of a person who has not been identified so far. Using the services a data space provides, the user can put in a request to discover photographs of the same person. If the data space integrates intelligent tools for image search based on similarity, photographs of the same person can be discovered in other archives or in newspaper collections! In fact, some of these collections might have metadata which would help to confirm the name of the person on the photograph, and where this photo had been taken. Using the data space goes beyond discovering the image but also adds valuable information, which our archivist lacked.
A more sophisticated example is illustrating how use cases can be built using several data spaces. The urban data space can use data from the data space for cultural heritage to create a rich layer of additional details on historical buildings. This can be used by a tourism data space for providing users with personalised cultural routes, in the spirit of an experimental work discussed by Pavel Kats and Alex Tursky in in September 2022 during the Europeana annual conference in the Hague.
Currently, a task force within the Europeana Aggregators Forum is exploring potential use cases and scenarios, if you are interested in this topic you could explore their work and possibly join the task force.
Publication details: Dobreva, M., Stefanov, K., Ivanova, K. (2022). Data Spaces for Cultural Heritage: Insights from GLAM Innovation Labs. In: Tseng, YH., Katsurai, M., Nguyen, H.N. (eds) From Born-Physical to Born-Virtual: Augmenting Intelligence in Digital Libraries. ICADL 2022. Lecture Notes in Computer Science, vol 13636. Springer, Cham. https://doi.org/10.1007/978-3-031-21756-2_41