• DARIAH EU
• 2012-2021close
• Open Access close
• EU close
• NARCIS close

This book is available as open access through the Bloomsbury Open programme and is available on www.bloomsburycollections.com. It is funded by Trinity College Dublin, DARIAH-EU and the European Commission.This book explores the challenges society faces with big data, through the lens of culture rather than social, political or economic trends, as demonstrated in the words we use, the values that underpin our interactions, and the biases and assumptions that drive us. Focusing on areas such as data and language, data and sensemaking, data and power, data and invisibility, and big data aggregation, it demonstrates that humanities research, focussing on cultural rather than social, political or economic frames of reference for viewing technology, resists mass datafication for a reason, and that those very reasons can be instructive for the critical observation of big data research and innovation.

This book is a collection of seventeen papers which describe the impact that the ARIADNE project and its successor, ARIADNEplus (2019-2022) have had on the archaeological community, both in Europe and further afield. Each case study has been contributed by organisations involved in the ARIADNE Infrastructure who cover many countries from across Europe as well as Argentina and Japan. These papers were originally presented at the CAA Conference in Krakow, April 2019 and cover aspects such as data management, application of standards and guidelines, the use of CIDOC-CRM and Open Data to name but a few.

In recent years, there has been a growing interest from the Digital Humanities in knowledge graphs as data modelling paradigm. Already, many data sets have been published as such and are available in the Linked Open Data cloud. With it, the nature of these data has shifted from unstructured to structured. This presents new opportunities for data mining. In this work, we investigate to what extend data mining can contribute to the understanding of archaeological knowledge, expressed as knowledge graph, and which form would best meet the communities' needs. A case study was held which involved the user-driven mining of generalized association rules. Experiments have shown that the approach yielded mostly plausible patterns, some of which were seen as highly relevant by domain experts.

Recent years have seen the emergence of graph-based Knowl-edge Bases build upon Semantic Web technologies, known as KnowledgeGraphs (KG). Popular examples are DBpedia and GeoNames. The formal system underlying these KGs provides inherent support for deductive reasoning. Growing popularity has exposed several limitations of thisability, amongst which are scalability and uncertainty issues, as well ascoping with heterogeneous, noisy, and inconsistent data. By supplementing this form of reasoning with Machine Learning algorithms, these hurdles are much more easily overcome. Of the existing research in this area,only a handful have been considering a Deep Neural Network. Moreover,only one of these studies has addressed the problem of hyper-parameteroptimization, albeit under specific conditions. To contribute to this areaof research, we propose a research design that will investigate a DeepNeural Network with optimized hyper-parameters for its effectiveness toperform link prediction on real-world KGs.

One of the funded project proposals under DARIAH’s Open Humanities call 2015 was “Open History: Sustainable digital publishing of archival catalogues of twentieth-century history archives”. Based on the experiences of the Collaborative EuropeaN Digital Archival Research Infrastructure (CENDARI) and the European Holocaust Research Infrastructure (EHRI), the main goal of the “Open History” project was to enhance the dialogue between (meta-)data providers and research infrastructures. Integrating archival descriptions – when they were already available – held at a wide variety of twentieth-century history archives (from classic archives to memorial sites, libraries and private archives) into research infrastructures has proven to be a major challenge, which could not be done without some degree of limited to extensive pre-processing or other preparatory work. The “Open History” project organized two workshops and developed two tools: an easily accessible and general article on why the practice of standardization and sharing is important and how this can be achieved; and a model which provides checklists for self-analyses of archival institutions. The text that follows is the article we have developed. It intentionally remains at a general level, without much jargon, so that it can be easily read by those who are non-archivists or non-IT. Hence, we hope it will be easy to understand for both those who are describing the sources at various archives (with or without IT or archival sciences degrees), as well as decision-makers (directors and advisory boards) who wish to understand the benefits of investing in standardization and sharing of data. It is important to note is that this text is a first step, not a static, final result. Not all aspects about standardization and publication of (meta-)data are discussed, nor are updates or feedback mechanisms for annotations and comments discussed. The idea is that this text can be used in full or in part and that it will include further chapters and section updates as time goes by and as other communities begin using it. Some archives will read through much of these and see confirmation of what they have already been implementing; others – especially the smaller institutions, such as private memory institutions – will find this a low-key and hands-on introduction to help them in their efforts. International audience

This report addresses the ARIADNE project objectives and the framework of the impact evaluation, summarises the overall results, and gives recommendations for ARIADNE and other stakeholders with a focus on potential further advances.