Computing Antiquity is a pioneering research initiative that brings computational methods to bear on the study of ancient Greek literature. By combining classical philology with state-of-the-art techniques in data science, the project opens new pathways for understanding the cultural, linguistic, and intellectual history of the ancient world.
Hosted at Aarhus University and supported by the Carlsberg Foundation, Computing Antiquity is developing one of the largest and most comprehensive open-access digital libraries of ancient Greek texts to date. This resource will offer scholars, students, and the general public access to thousands of historical works, many of which have previously been difficult to obtain in structured, machine-readable formats.
The project addresses several interlinked research questions. How can large-scale digital corpora reshape our understanding of genre, authorship, and intertextuality in classical literature? What patterns emerge when computational models are used to trace linguistic change across centuries of Greek writing? And to what extent can machine learning uncover previously unnoticed features in canonical texts?
Drawing on the expertise of philologists, computer scientists, and digital humanists, the team employs tools such as stylometry, topic modelling, and network analysis to study the evolution and transmission of ancient texts. The project also prioritises transparency and reproducibility, making both code and data publicly available for collaborative use and further experimentation.
By integrating traditional methods of textual interpretation with novel forms of algorithmic analysis, Computing Antiquity exemplifies how the humanities can thrive in dialogue with the digital. In doing so, it not only redefines how scholars engage with the past but also establishes a robust model for interdisciplinary research in the twenty-first century.
For more information and access to the digital library, visit computing-antiquity.au.dk.
Center for Humanities Computing (CHC) support the Computing Antiquity project with two core contributions relating to technical development and infrastructure provision. First, CHC has supported the collection and processing of large volumes of ancient Greek text and structuring them for subsequent computational analyses. Part of this work has involved providing best practice guidelines for file management and storage.
Second, CHC provides has created the project’s open access database and its corresponding website. Among other contributions, this consists of creating automated pipelines for importing and processing large amounts of metadata to ensure consistency and reliability in the database. The website allows for advanced filtering and search functionality in the database as well as the provision of text previews. Further, CHC manages files and file data related to the data in the database to allow users to download full text files or annotated (computationally analysed) files for further research. The website offers the option to combine this with filters and text search to batch download relevant full text or annotation files for multiple ancient texts.
Press release https://cas.au.dk/en/currently/news/show/artikel/aarhus-universitet-aabner-digitalt-bibliotek-for-antikke-graeske-tekster
Project Pure-website https://pure.au.dk/portal/en/projects/computing-antiquity
2022 - 2025
Collaborate with our Research Software Engineers, Data Scientists or Data Managers