VM

Selected research

All research

Paper explained

UNLP 2026 ACL Anthology Disinformation analysis

Graph-Based Detection of Disinformation Narrative Diffusion between Russian and Ukrainian Telegram Channels

Yuliia Vistak, Viktoriia Makovska, Vera Schmitt, Veronika Solopova

How do you follow a narrative when it is paraphrased and reposted?

The question

Why this work

Individual messages reveal only part of a disinformation campaign. This paper combines narrative labels with graph structure to examine how related claims circulate between Russian-language and Ukrainian-language Telegram channels.

The approach

A visual guide

Two ways to see a connection

Recorded forwardingSemantic similarity
  1. Messages

    Collect public posts and forwarding metadata.

  2. Narrative labels

    Assign related claims to a narrative inventory using weak supervision.

  3. Explicit forwards

    Use recorded source-channel links.

  4. Semantic links

    Find similar messages across channels even without a forward label.

Schematic network, not observed channel data. Solid links represent recorded forwarding; dashed links represent semantic similarity. Sections 3–5 and Limitations

What the work contributes

Semantic links identify similar content across channels even when native forwarding metadata records no connection. The two graph layers give different views of channel connectivity, showing why explicit forwards alone may understate narrative circulation.

Sections 3–5 and Limitations

Original paper & resources

In Proceedings of the Fifth Ukrainian Natural Language Processing Conference (UNLP 2026), pages 80-96, Lviv, Ukraine. Association for Computational Linguistics.

Citation
Vistak, Y., Makovska, V., Schmitt, V., & Solopova, V. (2026). Graph-Based Detection of Disinformation Narrative Diffusion between Russian and Ukrainian Telegram Channels. In Proceedings of the Fifth Ukrainian Natural Language Processing Conference (UNLP 2026), 80-96. Association for Computational Linguistics. https://aclanthology.org/2026.unlp-1.9/
BibTeX
@inproceedings{vistak-etal-2026-graph,
  title = {Graph-Based Detection of Disinformation Narrative Diffusion between {R}ussian and {U}krainian {T}elegram Channels},
  author = {Vistak, Yuliia and Makovska, Viktoriia and Schmitt, Vera and Solopova, Veronika},
  booktitle = {Proceedings of the Fifth {U}krainian Natural Language Processing Conference ({UNLP} 2026)},
  year = {2026},
  address = {Lviv, Ukraine},
  publisher = {Association for Computational Linguistics},
  pages = {80--96},
  url = {https://aclanthology.org/2026.unlp-1.9/}
}