“Ulpianus scripsit”? Using Artificial Intelligence for authorship attribution of ancient Roman law texts

Abstract

The present article seeks to demonstrate the usefulness of artificial intelligence for the exploration of the sources of Roman law. In a small experiment, a so-called support vector machine was employed to determine to which Roman jurist a given source text can be attributed. While the results were not perfect, they are sufficient to show the potential of new technologies for future research in the area.

Keywords

• artificial intelligence
• machine learning techniques
• sources of Roman law
• Ulpian
• authorship attribution