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

2026-06-28 · Source: Paper Index on ACL Anthology · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Data Science & Analytics, Cybersecurity & Data Privacy · Depth: Expert, quick

Summary

A new graph-based framework has been developed to identify and analyze disinformation narratives within Telegram ecosystems. This approach addresses the challenges of detecting disinformation, such as large-scale amplification, rapid evolution, and linguistic variability. It integrates weak supervision with propagation graph analysis to aggregate semantically related claims into narrative-level clusters. By modeling the diffusion of these clusters across interconnected channels, the framework effectively detects coordinated narrative amplification, a task difficult to achieve through post-level analysis alone. The findings indicate that combining textual signals with network structure offers a scalable method for detecting disinformation narratives and provides valuable insights into their propagation dynamics in large messaging environments.

Key takeaway

For intelligence analysts or researchers monitoring online disinformation, this graph-based framework offers a robust method to move beyond individual post analysis. You should consider integrating network structure with textual signals to identify coordinated narrative amplification more effectively. This approach provides scalable detection and deeper insights into how disinformation propagates across large messaging platforms like Telegram, enabling more proactive intervention strategies.

Key insights

Combining weak supervision and graph analysis detects disinformation narrative diffusion on Telegram more effectively than post-level analysis.

Principles

• Disinformation detection benefits from narrative-level clustering.
• Network structure reveals coordinated amplification.
• Textual signals enhance graph-based analysis.

Method

The framework aggregates semantically related claims into narrative clusters using weak supervision, then models their diffusion across channels via propagation graph analysis to detect coordinated amplification.

In practice

• Apply graph analysis to social media networks.
• Use weak supervision for claim aggregation.
• Monitor narrative diffusion across channels.

Topics

• Disinformation Detection
• Graph Analysis
• Telegram Channels
• Narrative Diffusion
• Weak Supervision

Best for: AI Scientist, Research Scientist, Data Scientist

Related on AIssential

• Exploring Knowledge Graphs for Automatic Fake News Detection in Portuguese — Knowledge Graphs offer an explainable method for automated fake news detection by modeling news as factual events.
• Noise Aggregation Analysis Driven by Small-Noise Injection: Efficient Membership Inference for Diffusion Models — Small-noise injection and noise aggregation analysis enable efficient membership inference against diffusion models.
• LLM-based Detection of Manipulative Political Narratives — A framework combines prompt-based filtering with unsupervised clustering to detect and structure manipulative political narratives.
• More information leads to more accurate beliefs—except in echo chambers — Echo chambers, even with free information flow, can reduce group belief accuracy by reinforcing existing, potentially inaccurate, views.
• Adversarial Creation and Detection of AI-Generated Social Bot Content — Adversarial training with paired human and AI-generated data significantly improves social bot content detection.
• On GATE, Text and Social Media Analysis, and Detecting Misinformation Online — A multi-layer analytical pipeline effectively extracts and categorizes digital identity aspects of agrifood products from online discourse.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Paper Index on ACL Anthology.