Paper explained
Graph-Based Detection of Disinformation Narrative Diffusion between Russian and Ukrainian Telegram Channels
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
Messages
Collect public posts and forwarding metadata.
Narrative labels
Assign related claims to a narrative inventory using weak supervision.
Explicit forwards
Use recorded source-channel links.
Semantic links
Find similar messages across channels even without a forward label.
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.
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/}
}