Computational authorship analysis of the homeric poems

Abstract Natural language modeling is used to predict or generate the next word character of modern languages. Furthermore, statistical character-based models have been found useful in authorship attribution analyses by studying linguistic proximity excerpts unknown model. In prior work, we modeled Homeric and provided empirical findings regarding nature 48 Iliad Odyssey books. Following this line considering current philological views trends, break down two poems further into smaller portions. By employing identify outlying passages, indicating reduced affinity with main body works and, extension, potentially different authorship. Our results show that some passages isolated as outliers were also identified such human researchers. We test our methodology on texts similar genre created other authors, namely Hesiod’s “Theogony” “Work Days”.