Hybrid topic modelling for computational close reading: Mapping narrative themes in Pushkin's Evgenij Onegin

TL;DR

This paper introduces a hybrid computational framework combining LDA and sPLS-DA to analyze themes and narrative structure in Pushkin's Evgenij Onegin, demonstrating its effectiveness in small-corpus literary analysis.

Contribution

It develops a novel hybrid modeling approach that integrates unsupervised and supervised techniques for thematic analysis in poetic texts, addressing small-corpus stability and interpretability.

Findings

Identified five stable, interpretable themes in Evgenij Onegin.

Enhanced thematic interpretability using supervised lexical markers.

Mapped narrative arcs and emotional structure through thematic hubs.

Abstract

This study presents a hybrid topic modelling framework for computational literary analysis that integrates Latent Dirichlet Allocation (LDA) with sparse Partial Least Squares Discriminant Analysis (sPLS-DA) to model thematic structure and longitudinal dynamics in narrative poetry. As a case study, we analyse Evgenij Onegin-Aleksandr S. Pushkin's novel in verse-using an Italian translation, testing whether unsupervised and supervised lexical structures converge in a small-corpus setting. The poetic text is segmented into thirty-five documents of lemmatised content words, from which five stable and interpretable topics emerge. To address small-corpus instability, a multi-seed consensus protocol is adopted. Using sPLS-DA as a supervised probe enhances interpretability by identifying lexical markers that refine each theme. Narrative hubs-groups of contiguous stanzas marking key episodes-extend the bag-of-words approach to the narrative level, revealing how thematic mixtures align with the poem's emotional and structural arc. Rather than replacing traditional literary interpretation, the proposed framework offers a computational form of close reading, illustrating how lightweight probabilistic models can yield reproducible thematic maps of complex poetic narratives, even when stylistic features such as metre, phonology, or native morphology are abstracted away. Despite relying on a single lemmatised translation, the approach provides a transparent methodological template applicable to other high-density literary texts in comparative studies.