The FIGNEWS Shared Task on News Media Narratives
Wajdi Zaghouani, Mustafa Jarrar, Nizar Habash, Houda Bouamor, Imed Zitouni, Mona Diab, Samhaa R. El-Beltagy, Muhammed AbuOdeh
2024-07-26
Summary
This paper provides an overview of the FIGNEWS shared task, which focuses on identifying bias and propaganda in news articles during the early days of the Israel War on Gaza. It involves collaboration among multiple teams to create guidelines for analyzing narratives in various languages.
What's the problem?
Identifying bias and propaganda in news articles is challenging because news can be presented in ways that favor certain viewpoints or mislead readers. This is especially important in multilingual contexts where different languages may convey information differently. The task aims to develop methods to automatically detect these biases in news content.
What's the solution?
The FIGNEWS shared task invited 17 teams to participate in annotating news articles for bias and propaganda across five languages: English, French, Arabic, Hebrew, and Hindi. Teams worked on two main subtasks: identifying bias (16 teams) and detecting propaganda (6 teams). They created a framework for analyzing narratives and produced a large dataset of 129,800 annotated data points. The task included evaluating how well the teams developed guidelines, the quality and quantity of their annotations, and their consistency in identifying bias and propaganda.
Why it matters?
This research is important because it helps improve our understanding of how bias and propaganda operate in news media, especially during critical events like wars. By developing better tools for detecting these issues, the findings can contribute to more reliable news reporting and help people critically evaluate the information they consume. This can lead to a more informed public and better media literacy.
Abstract
We present an overview of the FIGNEWS shared task, organized as part of the ArabicNLP 2024 conference co-located with ACL 2024. The shared task addresses bias and propaganda annotation in multilingual news posts. We focus on the early days of the Israel War on Gaza as a case study. The task aims to foster collaboration in developing annotation guidelines for subjective tasks by creating frameworks for analyzing diverse narratives highlighting potential bias and propaganda. In a spirit of fostering and encouraging diversity, we address the problem from a multilingual perspective, namely within five languages: English, French, Arabic, Hebrew, and Hindi. A total of 17 teams participated in two annotation subtasks: bias (16 teams) and propaganda (6 teams). The teams competed in four evaluation tracks: guidelines development, annotation quality, annotation quantity, and consistency. Collectively, the teams produced 129,800 data points. Key findings and implications for the field are discussed.