With an increasing number digitized historical archives, we also see a growing number of historians that rely on computational methods to examine such archives. This includes methods for retrieving textual and visual information from archives, studying the history of concepts, but also reflections on research practices and the construction of digitized archives. The HistoInformatics workshop series is focused on the challenges and opportunities of data-driven historical research and brings together scientists and scholars at the forefront of this emerging field, at the interface between historical disciplines on the one hand and informatics on the other. The 5th HistoInformatics workshop took place on September 12, 2019, and was a full-day workshop co-located with the 23rd International Conference on Theory and Practice of Digital Libraries (TPDL 2019) in Oslo.
Introduction to 5th HistoInformatics Workshop 2
HistoInformatics 2019 was a full-day workshop. The program chairs accepted six papers. The accepted papers are briefly described in what follows.
The paper Reflections on Design Principles for a Historical Archive in a Low Resource Environment discussed strategies for building digital archives in environments characterized by a lack of technical skills, facilitates, and/or funding. The authors of the paper LOCALE: A Rulebased Location Named-entity Recognition Method for Latin Text introduce a method for location extraction from Latin texts. The paper Clustering Ideological Terms in Historical Newspaper Data with Diachronic Word Embeddings studies the emergence of isms in nineteenth-century Finnish newspapers as a proxy for political language formation in Finland. The authors of Trawling for Terrorists: A Big Data Analysis of Conceptual Meanings and Contexts in Swedish Newspapers, 1780–1926 also turn to digitized newspaper archives. This paper traces the concept of terrorism over almost 150 years. The paper Character Segmentation in Collector’s Seal Images: An Attempt on Retrieval Based on Ancient Character Typeface turns to computer vision to construct a recognition system based for document retrieval of ancient Asian books. Finally, the authors of Plague Dot Text: Text Mining and Annotation of Outbreak Reports of the Third Plague Pandemic (1894-1952) describe the challenges related to an interdisciplinary research project that studies reports from the third plague pandemic (1894-1952).
The workshop also included a keynote by Mikko Tolonen, Assistant Professor in Digital Humanities at the University of Helsinki, Finland, titled: Integrated Computational Approach in Eighteenth-Century Intellectual History. The talk focused on strategy of the Helsinki Computational Group for combining computational methods with eighteenth-century intellectual history. 3
We would like to thank the program committee members for their effort in reviewing and recommending papers. We also thank the organizers of the TPDL 2019 conference for hosting and supporting our workshop, and also the anonymous reviewers who evaluated our proposal, for their constructive criticism. Finally, we would like to express our gratitude to our keynote speaker Mikko Tolonen.