Data and Knowledge Modelling as the Methodological Foundation of the Digital Humanities

Abstract

Digital humanities is a multidisciplinary field that leverages digital technology and methodologies to explore and answer questions pertaining to the humanities. It is a dynamic intersection between the domains of computer science and the humanities, promoting innovation, collaboration, and research at the highest levels. However, as a relatively young field, the methodological foundations of the digital humanities are still being established. This paper seeks to explore the core methodologies that underpin digital humanities. The modelling of data, information, and knowledge can be considered one of the foundations of digital humanities. One of the arguments confirming this is that the development of digital humanities and the development of technologies in general are the development of ways to formalise and present data and knowledge. Science has come a long way from the modelling and computer representation of numbers to generating texts and art on the basis of prescribed inputs. With the advent of artificial intelligence, especially machine learning and deep learning techniques, the potential for more sophisticated and nuanced data modelling in the digital humanities has expanded significantly, linking computational capabilities with humanistic inquiries in unprecedented ways. The article considers the periodization, classification, and trends of approaches and methods for modelling data, information and knowledge in the humanities. The article provides an overview of existing examples and data models of different complexity from various humanities disciplines, including history, linguistics, literary criticism, and cultural studies.