Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Dairazalia Sánchez-Cortés, Sergio Burdisso, Esaú Villatoro-Tello, Petr Motlicek

TL;DR

An extension to a recently presented news media reliability estimation method that focuses on modeling outlets and their longitudinal web interactions, suggesting that profiling news media sources based on their hyperlink interactions over time is feasible and offering a bird's-eye view of evolving media landscapes.

Abstract

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 CheckThat! 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.

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

TL;DR

An extension to a recently presented news media reliability estimation method that focuses on modeling outlets and their longitudinal web interactions, suggesting that profiling news media sources based on their hyperlink interactions over time is feasible and offering a bird's-eye view of evolving media landscapes.

Abstract

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 CheckThat! 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.

Paper Structure

This paper contains 10 sections, 1 figure, 3 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Methodology and Strategies
  4. Datasets
  5. Experiments and Results
  6. Factuality of Reporting
  7. Political Bias
  8. Conclusions
  9. Acknowledgments.
  10. Disclosure of Interests.

Figures (1)

  • Figure 1: Example showing how newrepublic.com relates with neighboring news sources. Left and Right wing sources are colored red and blue respectively, in addition, size of the node reflects the degree of the bias (learned by our I-political strategy). We can see that since newrepublic.com interacts mostly with Left-wing sources, its final bias degree ended up being considerable Left-wing.