CoChat
Sign Up
Cited by 21Misinformation and Its ImpactsHate Speech and Cyberbullying DetectionSentiment Analysis and Opinion Mining

The DOI matches its Crossref record; 28 of the 28 references it cites were found in a registry or an index.

Automated Multilingual Detection of Pro-Kremlin Propaganda in Newspapers and Telegram Posts

Open access
Solopova, Veronika, Popescu, Oana-Iuliana, Benzmüller, Christoph, Landgraf, Tim·2023·Datenbank-Spektrum
DOI 10.1007/s13222-023-00437-2
Open this paper in CoChat — free accountOpen PDF

Abstract

The full-scale conflict between the Russian Federation and Ukraine generated an unprecedented amount of news articles and social media data reflecting opposing ideologies and narratives. These polarized campaigns have led to mutual accusations of misinformation and fake news, shaping an atmosphere of confusion and mistrust for readers worldwide. This study analyses how the media affected and mirrored public opinion during the first month of the war using news articles and Telegram news channels in Ukrainian, Russian, Romanian, French and English. We propose and compare two methods of multilingual automated pro-Kremlin propaganda identification, based on Transformers and linguistic features. We analyse the advantages and disadvantages of both methods, their adaptability to new genres and languages, and ethical considerations of their usage for content moderation. With this work, we aim to lay the foundation for further development of moderation tools tailored to the current conflict.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1007/s13222-023-00437-2

Cites

28 of 28 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • The extraction script from [25] includes various morphological, syntactical, shallow semantic, and punctuation-based features.

    “This model includes various morphological features such as the number of different parts of speech and their types (e.g. verbs, modal and passive forms, proper, common, discourse markers, negations, comparatives, and superlatives), as well as syntactical features such as the frequency of different subordinate clauses (e.g. temporal, concession, clauses of reason, purpose, etc).”

    From Exploring incel group dynamics: a computational study of hierarchy and group-boundary policing (2025) · cites this paper as [25]

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Flagged first, then by citations

Research works printed but not linked: 12

  1. Carroll J (2017) Image and imitation the visual rhetoric of pro-russian propaganda. Ideol Polit J 8:36–79
  2. Dadu T, Pant K, Mamidi R (2020) Towards detection of subjective bias using contextualized word embeddings. CoRR, vol abs/2002.06644 · arXiv
  3. Gaufman E (2016) Security threats and public perception: digital russia and the Ukraine crisis. New security challenges
  4. Meister S (2016) The roots and instruments of Russia’s disinformation campaign (Transatlantic Academy, 2015-16 paper series, chap 3)
  5. Narayanan VP (2017) Russian involvement and junk news during brexit comprop data memo 2017.10
  6. NATO Strategic Communications Center of Excellence (2016) The manipulative techniques of russian’s information campaign, euro-atlantic values and russia’s strategic communication in euro-atlantic space (Tech. rep.)
  7. OED Online (2022) Propaganda vol 11. Oxford University Press, Oxford
  8. Oliinyk VA, Vysotska V, Burov Y, Mykich K, Fernandes VB (2020) Propaganda detection in text data based on nlp and machine learning. In: MoMLeT+DS
  9. Powers D (2008) Evaluation: From precision, recall and f‑factor to roc, informedness, markedness & correlation. Mach Learn Technol 2. https://doi.org/10.48550/arXiv.2010.16061 · DOI · Paper page
  10. Smith BL (2022) Propaganda. Encyclopedia Britannica, p 24
  11. US Department of State (2020) Pillars of russia’s disinformation and propaganda ecosystem (Tech. rep.)
  12. Wilbur D (2021) Propaganda or not: Examining the claims of extensive russian information operations within the united states. J Inf Warf 20:146–156

Cited by

Sorted by citations

Related

Metadata

Authors
Solopova, V., Popescu, O.-I., Benzmüller, C., & Landgraf, T.
Affiliations
  • Freie Universität Berlin (DE)
  • Deutsches Zentrum für Luft- und Raumfahrt e. V. (DLR) (DE)
Corresponding author
Solopova, Veronika
ORCID
Venue
Datenbank-Spektrum
Publisher
Springer Science and Business Media LLC
Published
2023-03
Volume
23
Issue
1
Pages
5-14
ISSN
  • 1610-1995 (ISSN-L)
  • 1618-2162
DOI
10.1007/s13222-023-00437-2
OpenAlex
W4323043532
Cited by
21
References
28
Citations by year
2026: 2 · 2025: 7 · 2024: 7 · 2023: 5
FWCI
9.02
Type
journal article
Language
en
Open access
Licence
Locations
Datenbank-Spektrum (publishedVersion, cc-by)
Funders
Freie Universität Berlin
Topics
  • Social Sciences › Sociology and Political Science › Misinformation and Its Impacts
  • Physical Sciences › Computer Science › Artificial Intelligence › Hate Speech and Cyberbullying Detection
  • Physical Sciences › Computer Science › Artificial Intelligence › Sentiment Analysis and Opinion Mining
Keywords
Russian invasion of Ukraine, misinformation detection, multilingual text classification, news articles, transformer models, linguistic features, content moderation, propaganda detection, public opinion

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review