By Patricia Murrieta-Flores & Katherine Bellamy
The project ‘Digging into Early Colonial Mexico: A large-scale computational analysis of sixteenth-century historical sources’ (DECM) at the University of Lancaster is developing novel methods and tools for mining data from both textual and pictorial historical records.
Using Geographical Information Systems (GIS), Natural Language Processing (NLP), and Machine Learning, the project aims to create new ways of answering vital research questions which would previously have required a lifetime of investigation.They are experimenting with NLP annotation models to enable the automatic extraction of information by topic, as well as the automated recognition of proper names including toponyms, institutions and people’s names, and are in the process of creating the first digital 16th century gazetteer of New Spain through the semi-automated extraction and disambiguation of place-names from a number of historical secondary and primary sources. Read more about the project and it’s objectives here