cs.CL · 2606.09543 Copy arXiv ID · Jun 8, 2026 Save From Genes to Tokens: a GWAS-inspired Approach for Interpretable Stylometric Analysis Authors: Dmitry Pronin , Evgeny Kazartsev
Organizations: HSE University
Abstract This short paper introduces a stylometric interpretation method inspired by genome-wide association studies (GWAS). Each "gene" token's association with "phenotype" authorship is tested using logistic regression with multiple-comparison correction. Applied to English, German, and Russian corpora, the method detects statistically significant lexical markers distinctive of individual authors.
Explore similar work Apr 21, 2026 · Dmitry Pronin, Evgeny Kazartsev Stylometric Authorship
Sep 22, 2026 · Rajesh Kumar, Nabeel Siddiqui, Alexander Fuchsberger Machine-Generated Text Detection Human Annotators
Sep 8, 2026 · Gennadii Iakovlev, Levente Littvay Stylometric Authorship
Apr 21, 2026 · cs.CL J/K move · Enter open · S save
Dmitry Pronin, Evgeny Kazartsev
HSE University
This article introduces two new measures for authorship attribution - Rank-Turbulence Delta and Jensen-Shannon Delta - which generalise Burrows's classical Delta by applying distance functions designed for probabilistic distributions. We first set out the theoretical basis of the measures, contrasting centred and uncentred z-scoring of word-frequency vectors and re-casting the uncentred vectors as probability distributions. Building on this representation, we develop a token-level decomposition that renders every Delta distance numerically interpretable, thereby facilitating close reading and the validation of results. The effectiveness of the methods is assessed on four literary corpora in English, German, French and Russian. The English, German and French datasets are compiled from Project Gutenberg, whereas the Russian benchmark is the SOCIOLIT corpus containing 639 works by 89 authors spanning the eighteenth to the twenty-first centuries. Rank-Turbulence Delta attains attribution accuracy comparable with Cosine Delta; Jensen-Shannon Delta consistently matches or exceeds the performance of canonical Burrows's Delta. Finally, several established attribution algorithms are re-evaluated on the extended SOCIOLIT corpus, providing a realistic estimate of their robustness under pronounced temporal and stylistic variation.