Computational Analysis of Narratives and the Organization of Novels

Objetivo

Large collections of literary texts contain invaluable knowledge for understanding narratives, the evolution of literary genres, and, more broadly, the development of human culture. However, no method currently exists that can fully unlock the depth of insight contained in these corpora. While human analysis struggles to scale, automated approaches often remain superficial, failing to grasp the structure of narratives or accurately reflect their complexity. Narratology—the study of narrative forms and functions—thus remains a particularly challenging domain where computational tools cannot replace human expertise and interpretation. The goal of our project is to develop a novel approach that combines the strengths of distant and close reading, enabling narratological analysis at scale. Our method builds on new natural language processing (NLP) techniques designed specifically for large fictional corpora, yielding representations that retain textual complexity and support human interpretation. These models will be informed by concepts from narratology and literary theory, two areas largely overlooked in existing NLP research. We will first apply this methodology to large French literary corpora (which, for example, account for 40% of published novels in the 19th century) that have not yet been studied in depth and for which no appropriate computational tools currently exist. We will then explore how similar techniques can be applied to Russian literary corpora, with a particular focus on tracing the influence of French literature—especially the international role played by women authors—on the formation of modern Russian fiction. This comparative approach will help demonstrate the adaptability of our method to new languages, and its relevance for cross-cultural studies in narratology. Ultimately, the project aims to transform literary analysis and open new pathways for understanding cultural evolution through large, previously underexplored collections of novels.

Ámbito científico (EuroSciVoc)

Este proyecto aún no se ha clasificado con EuroSciVoc.
Sugiera los ámbitos científicos que considere más relevantes y ayúdenos a mejorar nuestro servicio de clasificación.