How can language technologies and geospatial analysis facilitate answering important questions about the early colonisation of America? How did the Spanish colonial authorities portray and use information about the newly conquered territories and people? Can we identify, map, and analyse the geographies associated with the colonial period of Mexico, and what was said about them in historical sources, through expedite computational means?
Using part of the corpus known as Relaciones Geográficas de la Nueva España – one of the most important colonial historical sources of America – concerned with the territory of Mexico, this project is creating and developing novel computational approaches for the semi-automated exploration of thousands of pages contained in these 16th century documents.
Tackling important historical and methodological questions, and highly demanding challenges in the study of these written sources, we are extracting, analysing, and visualising information that can improve our understanding of this period, and expedite the process by which we study these documents.
Our highly interdisciplinary team is combining techniques from different disciplines, including Corpus Linguistics, Text Mining, Natural Language Processing, Machine Learning, and Geographic Information Systems, to address questions related to the recording of information about indigenous cultures, the Spanish exploration of indigenous social and religious concepts, the appropriation and ideas about place and space in the indigenous world, and their attitudes towards politics and economy.