Digital Approaches to Historical Archaeology: Exploring the Geographies of 16th Century New Spain

The humanities have always been concerned with ideas of space, place and time. However, in the past few years, and with the emergence of Digital Humanities and Computational Archaeology, researchers have started to apply an array of computational methods and geographical analysis tools in order to understand the role that space plays in the historical processes of human societies. As a result, historians and archaeologists, together with computer scientists, are currently developing digital approaches that can be used to address questions and solve problems regarding the geographies contained in documentary sources such as texts and historical maps. Digging into Early Colonial Mexico is an interdisciplinary project that applies a Data Science/Big Data approach to historical archaeology, focusing on the analysis of one of the most important historical sources of the 16th century in Latin America, called the Geographic Reports of New Spain. The purpose of this paper is to

a) describe the nature of the historical corpus,

b) introduce the methodologies and preliminary results produced so far by the project, and

c) explain some of the theoretical and technical challenges faced throughout the development of the methods and techniques that supported the analysis of the historical corpus.

Keywords: Historical archaeology; Digital humanities; Spatial humanities; New spain; Geographic information sciences; Machine learning; Natural language processing; Corpus linguistics; Geographical text analysis; FAIR data

Abbreviations: AI: Artificial Intelligence; CA: Collocation Analysis; CONABIO: Comisión Nacional para el Conocimiento y Uso de la Biodiversidad; CL: Corpus Linguistics; DECM: Digging into Early Colonial Mexico; ENAH: Escuela Nacional de Antropología e Historia; FAIR: Findable, Accessible, Interoperable, and Reusable Data; GISc: Geographic Information Sciences; GIS: Geographic Information Systems; GTA: Geographical Text Analysis; INAH: Instituto Nacional de Antropología Historia; INEGI: Instituto Nacional; de Estadística Geografía e Informatic; KML: Keyhole Markup Language; LOD: Linked Open Data; ML: Machine Learning; NER: Named Entity Recognition; NLP: Natural Language Processing; OCR: Optical Character Recognition; RGs: Relaciones Geográficas de Nueva España; UNAM: Universidad Nacional Autónoma de México