--- title: "Rostislav Petrov — author profile and papers" description: "Rostislav Petrov: 2 papers on Elamur Research (2019–2020), h-index 4 — affiliations, topics, co-authors and who cites them in our library." canonical: "https://research.elamur.ai/free/en/authors/rostislav-petrov/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/rostislav-petrov/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Rostislav Petrov # Rostislav Petrov Rostislav Petrov's papers here deal with the automatic detection of propaganda in news writing. The recurring question is where, within an article, persuasive techniques appear and which technique each passage uses, rather than whether an entire document or news source is biased. The work relies on news articles that professional annotators marked at the level of individual text spans, and it frames the problem as sequence tagging paired with multi-class classification. The most cited paper, [Fine-Grained Analysis of Propaganda in News Articles](https://md.research.elamur.ai/free/en/papers/martino-2019-fine-grained-analysis-propaganda-news/) (2019), argues that labels copied from the publishing outlet are noisy and cannot explain a prediction. It proposes instead to pinpoint the fragments that employ a technique and to name that technique. Its modelling ideas include a gate in which sentence-level output switches off token-level predictions in sentences judged free of propaganda, with the choice of gating function adjusted to how reliable the signal is. Nearly as widely cited is [SemEval-2020 Task 11](https://md.research.elamur.ai/free/en/papers/martino-2020-semeval-2020-task-11-detection/), which turned this framing into an open evaluation for many participating systems. The newer of these papers moves from a single study to a common benchmark. Because the combined find-and-label problem produced very low scores, the shared task splits it into span identification and technique classification, so that each part can be studied on its own. It also merges sparse, similar labels only after annotation, and it keeps only techniques that can be decided from the article's wording without consulting outside sources. Petrov's papers here were written with [Giovanni Da San Martino](https://md.research.elamur.ai/free/en/authors/giovanni-da-san-martino/), [Alberto Barrón-Cedeño](https://md.research.elamur.ai/free/en/authors/alberto-barron-cedeno/) and [Preslav Nakov](https://md.research.elamur.ai/free/en/authors/preslav-nakov/), who appear on both. [Henning Wachsmuth](https://md.research.elamur.ai/free/en/authors/henning-wachsmuth/) is a co-author on one of them. Rostislav Petrov has 2 papers in our library, in 2019–2020; often with [Alberto Barrón-Cedeño](https://md.research.elamur.ai/free/en/authors/alberto-barron-cedeno/), [Giovanni Da San Martino](https://md.research.elamur.ai/free/en/authors/giovanni-da-san-martino/), [Preslav Nakov](https://md.research.elamur.ai/free/en/authors/preslav-nakov/). 2 papers in our library · 2019–2020 [OpenAlex](https://openalex.org/A5038473194) · [**h-index 4**](https://openalex.org/authors/A5038473194) · [6 works](https://openalex.org/works?filter=author.id:A5038473194) · [597 citations](https://openalex.org/works?filter=author.id:A5038473194&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [2 works in our library](https://md.research.elamur.ai/free/en/authors/rostislav-petrov/#papers) · [266 citations in our library](https://md.research.elamur.ai/free/en/authors/rostislav-petrov/cited-by/) · [⭐ Paper Star rank #2379](https://md.research.elamur.ai/free/en/paper-stars/page/24/#star-2379) The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Rostislav+Petrov) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Rostislav+Petrov) · [dblp](https://dblp.org/search?q=Rostislav+Petrov) · [ACL Anthology](https://aclanthology.org/search/?q=Rostislav+Petrov) ## Works by year ### 2020s [**2020** 1 paper](https://md.research.elamur.ai/free/en/papers/martino-2020-semeval-2020-task-11-detection/) ### 2010s [**2019** 1 paper](https://md.research.elamur.ai/free/en/papers/martino-2019-fine-grained-analysis-propaganda-news/) ## Papers The most cited first (OpenAlex and our library). 1. **[Fine-Grained Analysis of Propaganda in News Articles](https://md.research.elamur.ai/free/en/papers/martino-2019-fine-grained-analysis-propaganda-news/)** *(2019 · 379 citations)* Most earlier propaganda detection work labels whole articles, often by copying the label of the news outlet that published them. 2. **[SemEval-2020 Task 11: Detection of Propaganda Techniques in News Articles](https://md.research.elamur.ai/free/en/papers/martino-2020-semeval-2020-task-11-detection/)** *(2020 · 371 citations)* This shared task moves propaganda detection from whole articles down to the level of individual text fragments. ## Co-authors here 4 co-authors with a page, the most papers together first. - [Alberto Barrón-Cedeño](https://md.research.elamur.ai/free/en/authors/alberto-barron-cedeno/) ×2 - [Giovanni Da San Martino](https://md.research.elamur.ai/free/en/authors/giovanni-da-san-martino/) ×2 - [Preslav Nakov](https://md.research.elamur.ai/free/en/authors/preslav-nakov/) ×2 - [Henning Wachsmuth](https://md.research.elamur.ai/free/en/authors/henning-wachsmuth/) ## Cited by Papers of our library cite their works 266 times (of the 140 884 papers whose bibliographies we read); [7 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/rostislav-petrov/cited-by/).