Project duration: 2022 - 2026 Date coverage: 1600 - 1800 Website Contact

AI Archive Crowdsourcing / Citizens’ science Digital Humanities Digital Infrastructure Historical Documents (e.g. Notarial sources; Census records; Ecclesiastical documents; Correspondence) Knowledge Graph Linked Data Machine Learning Natural language processing (NLP) OCR / HTR Paleography Persons data Socio-Economic History Tools for data mining/extraction

GLOBALISE (General Letters Ontology-Based AccessibiLity InfraStructurE, 2022-2026) aims to unlock the key series of documents and reports in the archives of the Dutch East India Company (VOC) for advanced new research methods. This archival series of more than 5 million handwritten pages, kept in the Dutch National Archives in The Hague, is of irrefutable value for reconstructing the history of the vast region around the Indian Ocean and Indonesian archipelago where the VOC was active from 1602 until 1798. For some regions, documents in the VOC archives are among the earliest written historical sources.

The GLOBALISE project will produce full transcripts of the source material, as well as reference datasets, thesauri and ontologies as Linked Open Data (LOD). We will publish these over the course of the project and make them jointly accessible in an online research infrastructure that allows researchers to browse and search the scans and their full transcripts in relation to our linked reference data. In this infrastructure, users will among other things be able to search for named entities (e.g. persons or locations) and events (e.g. ship voyages or political disputes), and query relationships between these entities and events.

Project partners

With financial support by