Following our call for papers in the September, we are delighted that seven article-length tutorials will now go forward for publication as part of this special series. The submissions were of the highest quality, and although we couldn’t selected them all, we thank all who submitted - you certainly made it hard for us to choose!
The selected articles will introduce readers to a range of approaches to analysing large-scale collections: using neural networks as a research tool, creating visual clusters of documents, making interactive visualisations, working with word embeddings, summarising web archive content, extracting data from handwriting documents. And - subject to peer review - they will be published in our Portuguese, French, and English publications, with localised translations appearing thereafter.
One thing that is clear at this earlier stage is that the selected articles will challenge our processes and infrastructure. For example, the importance the Programming Historian places on publishing articles for the long-term is in clear tension with supporting the development of articles based on emerging technologies such as deep learning. Equally, whilst digital humanities workflows often interact with large-scale datasets using cloud computing services, the fact that are often not openly accessible creates difficulties in how authors construct articles that meet our global ambitions. Nevertheless, we look forward to working through these challenges, and are confident that we will emerge from the process a publisher better able to support tutorials on complex analytical processes.
This special series forms the major output of the project ‘Programming Historian publications: developing computational skills for digital collections’, a partnership between Jisc, the Programming Historian, and The National Archives. For more information on the partnership see the partnership announcement.
About the author
James Baker is Director of Digital Humanities at the University of Southampton.