ExU: AI Models for Examining Multilingual Disinformation Narratives and Understanding their Spread

TL;DR

The ExU project develops AI models to analyze multilingual disinformation narratives, aiding fact-checkers in identifying and understanding false information across languages.

Contribution

It introduces AI-based models for multilingual disinformation analysis, focusing on rumour stance classification and claim retrieval, with insights from user requirements surveys.

Findings

User requirements survey results inform tool design

Development of AI models for multilingual disinformation tasks

Initial results show potential for aiding fact-checkers

Abstract

Addressing online disinformation requires analysing narratives across languages to help fact-checkers and journalists sift through large amounts of data. The ExU project focuses on developing AI-based models for multilingual disinformation analysis, addressing the tasks of rumour stance classification and claim retrieval. We describe the ExU project proposal and summarise the results of a user requirements survey regarding the design of tools to support fact-checking.