Profile

I develop interpretable methods for analysing literary style, authorship, and text corpora. I work as a programmer and visiting lecturer at HSE University and am a core developer of SOCIOLIT and PROZIMETRON. My publications include a peer-reviewed article in Digital Scholarship in the Humanities and a textbook on digital philology. At DH2026, I presented research and chaired a session.

Research interests: interpretable stylometry; authorship attribution; digital literary studies; corpus linguistics; explainable NLP; large language models.

Digital Humanities 2026

Presenter

From Genes to Tokens: a GWAS-inspired Approach for Interpretable Stylometric Analysis, with Evgeny Kazartsev. Session S072, 30 July 2026, Room 107.

Open preprint ↗

Session chair

Session S026 on linked open data, historical information retrieval, and rumour discovery. 29 July 2026, Room 103.

Academic and research experience

HSE University

2025–present

Programmer and visiting lecturer · School of Philological Studies, Faculty of Humanities · Moscow

  • Develop statistical and NLP methods for literary-text analysis, with an emphasis on interpretability, validation, and reproducibility.
  • Core developer of SOCIOLIT and PROZIMETRON: analytical modules, corpus pipelines, APIs, and interfaces for researchers.
  • Co-instructor of the BA course Literature and Digital Humanities in 2025/26.

Bauman Moscow State Technical University

2024–present

Team lead and Python developer · Research and Education Center · Moscow

  • Lead research-software development, testing, and integration of Python components.
  • Develop statistical text-analysis methods and large-language-model applications.

Education

HSE University

2025–present

MA programme in Digital Methods in the Humanities · Moscow.

Bauman Moscow State Technical University

2021–2025

BSc in Control in Technical Systems, specialising in Intelligent Control and Data Processing Systems · Moscow.

Selected research projects

SOCIOLIT

A Russian literary analytics platform. Contributed a corpus of 755 works by 180 authors spanning the eighteenth to twenty-first centuries.

SOCIOLIT platform ↗

PROZIMETRON

Comparative analysis of verse and prose: accentual annotation, rhythm modelling, probabilistic comparison, and multilingual workflows.

Interpretable Delta measures

Rank-Turbulence and Jensen–Shannon Delta, token-level decompositions, and stability validation.

Code and notebooks ↗

GWAS-inspired stylometry

Logistic-regression association testing with multiple-comparison correction to study lexical associations with authorship.

Code and notebooks ↗

Selected publications

Pronin, D., & Kazartsev, E. (2026). Rank-Turbulence Delta and interpretable approaches to stylometric Delta measures. Digital Scholarship in the Humanities, 41(3), 1616–1630.

DOI 10.1093/llc/fqag072 ↗

Pronin, D., & Kazartsev, E. (2026). From Genes to Tokens: a GWAS-inspired Approach for Interpretable Stylometric Analysis. Short paper presented at DH2026; preprint arXiv:2606.09543.

Open preprint ↗

Kazartsev, E., Pronin, D., & Kirina, M. (forthcoming). Digital Literary Studies at the New Russian Computational Platform SOCIOLIT. In Proceedings of the 37th Conference of Open Innovations Association FRUCT. IEEE.

HSE publication record ↗

Kazartsev, E., & Pronin, D. (2024). Fundamentals of Digital Philology: Methods and Principles of Computer-Assisted Text Analysis. St Petersburg: Politekhnika. 178 pp. In Russian.

Technical profile

Python, SQL, Git; R for research; pandas, NumPy, SciPy, scikit-learn, statsmodels; Django and REST APIs. Stylometry, corpus processing, statistical modelling, clustering, data visualisation, and LLM applications.

Science communication and awards