Narratives at Conflict: Computational Analysis of News Framing in Multilingual Disinformation Campaigns
This addresses the problem of detecting multilingual disinformation framing for researchers and policymakers, though it is incremental in highlighting model limitations.
The study analyzed how Russia-backed disinformation campaigns systematically vary news framing across 8,000 articles in 4 languages targeting 15 countries, finding that framing is intentionally tailored to audience language and region. It also revealed that existing automatic frame analysis models underperform with high disagreement, indicating a need for improved methods.
Any report frames issues to favor a particular interpretation by highlighting or excluding certain aspects of a story. Despite the widespread use of framing in disinformation, framing properties and detection methods remain underexplored outside the English-speaking world. We explore how multilingual framing of the same issue differs systematically. We use eight years of Russia-backed disinformation campaigns, spanning 8k news articles in 4 languages targeting 15 countries. We find that disinformation campaigns consistently and intentionally favor specific framing, depending on the target language of the audience. We further discover how Russian-language articles consistently highlight selected frames depending on the region of the media coverage. We find that the two most prominent models for automatic frame analysis underperform and show high disagreement, highlighting the need for further research.