Identifying the stylistic signatures characteristic of different genres is of central importance to literary theory and criticism. In this article we report a large-scale computational analysis of Latin prose and verse using a combination of quantitative stylistics and supervised machine learning. We train a set of classifiers to differentiate prose and poetry with high accuracy (>97%) based on a set of twenty-six text-based, primarily syntactic features and rank the relative importance of these features to identify a low-dimensional set still sufficient to achieve excellent classifier performance. This analysis demonstrates that Latin prose and verse can be classified effectively using just three top features. From examination of the highly ranked features, we observe that measures of the hypotactic style favored in Latin prose (i.e. subordinating constructions in complex sentences, such as relative clauses) are especially useful for classification.

No abstract

Authors often convey meaning by referring to or imitating prior works of literature, a process that creates complex networks of literary relationships ("intertextuality") and contributes to cultural evolution. In this paper, we use techniques from stylometry and machine learning to address subjective literary critical questions about Latin literature, a corpus marked by an extraordinary concentration of intertextuality. Our work, which we term "quantitative criticism," focuses on case studies involving two influential Roman authors, the playwright Seneca and the historian Livy. We find that four plays related to but distinct from Seneca's main writings are differentiated from the rest of the corpus by subtle but important stylistic features. We offer literary interpretations of the significance of these anomalies, providing quantitative data in support of hypotheses about the use of unusual formal features and the interplay between sound and meaning. The second part of the paper describes a machine-learning approach to the identification and analysis of citational material that Livy loosely appropriated from earlier sources. We extend our approach to map the stylistic topography of Latin prose, identifying the writings of Caesar and his near-contemporary Livy as an inflection point in the development of Latin prose style. In total, our results reflect the integration of computational and humanistic methods to investigate a diverse range of literary questions.authorship attribution | cultural evolution | intertextuality | machine learning | stylometry T he study of literature relies on mapping interactions between texts. Ancient Greek critics understood the tragedies of Aeschylus in part through their relation to Homeric epic, and ancient Roman commentators interpreted words and phrases in texts by citing parallels in other works. Much of literary criticism today rests on understanding these vast networks of intertextuality, which often have profound consequences for the meaning of both individual texts and larger groupings by genre or period (1). Through quantitative analysis of formal elements and their change over time, the study of intertextuality can shed light on the cultural evolution of literature (2).A central challenge in the study of intertextuality is its heterogeneous nature. Literary parallels differ widely in both similarity and scope (Fig. 1A). The relationship between the associated texts can range from obvious (direct quotation) to extremely subtle (artfully constructed indirect references, often referred to as allusions in literary study). Furthermore, parallels can operate on the level of individual words or phrases, short passages, or entire works and can involve verbal, syntactic, phonetic, or metrical features. As illustrated in Fig. 1A, intertexts can be of comparable similarity but very different scope; an adaptation of an entire work, for instance, can be thought of as a collection of many (local) allusions.In this paper, we focus on the quantitative characterization of intertextual rela...

Classification of texts by genre is an important application of natural language processing to literary corpora but remains understudied for premodern and non-English traditions. We develop a stylometric feature set for ancient Greek that enables identification of texts as prose or verse. The set contains over 20 primarily syntactic features, which are calculated according to custom, language-specific heuristics. Using these features, we classify almost all surviving classical Greek literature as prose or verse with >97% accuracy and F1 score, and further classify a selection of the verse texts into the traditional genres of epic and drama.