This article demonstrates that metre is a privileged indicator of authorial style in classical Latin hexameter poetry. Using only metrical features, classification experiments are performed between the works of six authors using four different machine-learning models. The results showed a pairwise classification accuracy of at least 90% with samples as small as ten lines and no greater than seventy-five lines (up to around 500 words). In a multiclass setting, classification accuracy exceeded 95% for all four algorithms when using eighty-one-line chunks. These sample sizes are an order of magnitude smaller than those typically recommended for BOW (‘bag of words’) or n-gram approaches, and the reported accuracy is outstanding. Additionally, this article explores the potential for outlier (forgery) detection, or ‘one-class classification’. As an example, analysis of the disputed Aldine Additamentum (Sil. Ital. Pun. 8:144–223) concludes (P < 0.0001) that the metrical style differs significantly from that of the rest of the poem.

This study offers the first broad quantitative analysis of the use of rhyme in classical Latin hexameter and elegiac verse. The data and tools developed for the analysis are released under a permissive open source license. These include software to create an accurate phonetic transcription of Latin verse from the Musisque Deoque corpus; a system for scoring rhyme via phonetic similarity; and a system for generating large amounts of metrically correct, stochastic Latin verse (useful for analysis baselines). Further to this, some initial analysis is performed: first via descriptive statistics and then with two unsupervised multivariate analyses using dimension reduction methods. The study examines nineteen works by twelve authors, comprising about 96,000 lines. First and foremost, the results suggest that rhyme was consciously used by classical authors, but to different extents and in different ways. There is a solid and detectable stylistic separation between the use of rhyme in elegy and epic, and possibly also between satire and the rest. Within genres, authors can be stylistically separated with a small set of features. On the negative side, it appears that the stylistic signal from rhyme is fairly faint, and so forensic analysis (e.g. for authorship attribution) is not presently recommended on texts that are shorter than several thousand lines.

No abstract

This article contributes to two well-worn areas of debate in classical Latin philology, relating to Ovid’s Heroides. The first is the question of the authenticity (and, to a lesser extent the correct position) of the letter placed 15th in almost every collection—the so-called Epistula Sapphus (henceforth ES). The secondary question, although perhaps now less fervently debated, is the authenticity of the ‘Double Heroides’, placed by those who accept them as letters 16–21. I employ a variety of methods drawn from the domain of computational stylometry to consider the poetics and the lexico-grammatical features of these elegiac poems in the broader context of a corpus of ‘shorter’ (from 20 to 546 lines) elegiac works from five authors (266 poems in all) representing most of classical elegy. Based on a variety of techniques, every measure gives clear indication that the poetic style of the Heroides is genuinely Ovidian, but distinctive; they can be accurately isolated from Ovid more broadly. The Single and Double Heroides split into two clear groups, with the ES grouped consistently with the single letters. Furthermore, by comparing the style of the letters with the ‘early’ (although there are complications in this label) works of the Amores and the late works of the Ex Ponto, the evidence supports sequential composition—meaning that the ES is correctly placed—and, further, supports the growing consensus that the double letters were composed significantly later, in exile.

No abstract