Mapping the Media Landscape: Predicting Factual Reporting and Political Bias Through Web Interactions

Mapping the Media Landscape: Predicting Factual Reporting and Political Bias Through Web Interactions

Stať ve sborníku v databázi WoS či Scopus

Bias assessment of news sources is paramount for professionals, organizations, and researchers who rely on truthful evidence for information gathering and reporting. While certain bias indicators are discernible from content analysis, descriptors like political bias and fake news pose greater challenges. In this paper, we propose an extension to a recently presented news media reliability estimation method that focuses on modeling outlets and their longitudinal web interactions. Concretely, we assess the classification performance of four reinforcement learning strategies on a large news media hyperlink graph. Our experiments, targeting two challenging bias descriptors, factual reporting and political bias, showed a significant performance improvement at the source media level. Additionally, we validate our methods on the CLEF 2023 Check-That! Lab challenge, outperforming the reported results in both, F1-score and the official MAE metric. Furthermore, we contribute by releasing the largest annotated dataset of news source media, categorized with factual reporting and political bias labels. Our findings suggest that profiling news media sources based on their hyperlink interactions over time is feasible, offering a bird's-eye view of evolving media landscapes.

Bias assessment of news sources is paramount for professionals, organizations, and researchers who rely on truthful evidence for information gathering and reporting. While certain bias indicators are discernible from content analysis, descriptors like political bias and fake news pose greater challenges. In this paper, we propose an extension to a recently presented news media reliability estimation method that focuses on modeling outlets and their longitudinal web interactions. Concretely, we assess the classification performance of four reinforcement learning strategies on a large news media hyperlink graph. Our experiments, targeting two challenging bias descriptors, factual reporting and political bias, showed a significant performance improvement at the source media level. Additionally, we validate our methods on the CLEF 2023 Check-That! Lab challenge, outperforming the reported results in both, F1-score and the official MAE metric. Furthermore, we contribute by releasing the largest annotated dataset of news source media, categorized with factual reporting and political bias labels. Our findings suggest that profiling news media sources based on their hyperlink interactions over time is feasible, offering a bird's-eye view of evolving media landscapes.

news media profiling, media bias descriptors, factual reporting, political bias

news media profiling, media bias descriptors, factual reporting, political bias

SANCHEZ-CORTES, D.; BURDISSO, S.; VILLATORO-TELLO, E.; MOTLÍČEK, P.

2026

01.01.2024

Springer Nature

CHAM

978-3-031-71735-2

Lecture Notes in Computer Science

Lecture Notes in Computer Science

14958

Švýcarská konfederace

127

138

12

Sanchez-Cortes_CLEF2024_2024