Linking early geospatial documents, one place at a time: annotation of geographic documents with Recogito

Recogito is an open source tool for the semi-automatic annotation of place references in maps and texts. It was developed as part of the Pelagios 3 research project, which aims to build up a comprehensive directory of places referred to in early maps and geographic writing predating the year 1492. Pelagios 3 focuses specifically on sources from the Classical Latin, Greek and Byzantine periods; on Mappae Mundi and narrative texts from the European Medieval period; on Late Medieval Portolans; and on maps and texts from the early Islamic and early Chinese traditions. Since the start of the project in September 2013, the team has harvested more than 120,000 toponyms, manually verifying almost 60,000 of them. Furthermore, the team held two public annotation workshops supported through the Open Humanities Awards 2014. In these workshops, a mixed audience of students and academics of different backgrounds used Recogito to add several thousand contributions on each workshop day. A number of benefits arise out of this work: on the one hand, the digital identification of places – and the names used for them – makes the documents' contents amenable to information retrieval technology, i.e. documents become more easily searchand discoverable to users than through conventional metadata-based search alone. On the other hand, the documents are opened up to new forms of re-use. For example, it becomes possible to “map” and compare the narrative of texts, and the contents of maps with modern day tools like Web maps and GIS; or to analyze and contrast documents’ geographic properties, toponymy and spatial relationships. Seen in a wider context, we argue that initiatives such as ours contribute to the growing ecosystem of the “Graph of Humanities Data” that is gathering pace in the Digital Humanities (linking data about people, places, events, canonical references, etc.), which has the potential to open up new avenues for computational and quantitative research in a variety of fields including History, Geography, Archaeology, Classics, Genealogy and Modern Languages.