2025/03/01 by Thomas J. Bolt, Elizabeth D. Adams, Zafeirios Adramerinas +7 · 2 voices
Computer Science · #Authorship Attribution and Profiling
paper · doi:10.1353/apa.2025.a957882
openalex publication_date 2025/03/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/06/11
summary: Despite impressive advances in computational philology for attribution and textual criticism, more general questions of classical literary criticism remain underserved by quantitative methods. This article uses machine learning and exploratory data analysis to address such questions regarding the stylistics of genre and character speech in Latin literature. We describe a set of interpretable features, largely comprising function words and syntactic elements, and show how they can reveal distinguishing aspects of genres, subgenres, and individual characters. In the final part of the article, we present a complete critical workflow, which begins with open-ended exploration of mortal and divine speech in Latin epic and culminates with the testing of specific hypotheses about Vergil's Juno and Juturna.