A Multi-View Media Profiling Suite: Resources, Evaluation, and Analysis

2026-05-02

AI Summary

This study addresses the lack of unified resources and systematic cross-method evaluation in media bias and factuality detection, particularly under label sparsity and dataset heterogeneity. To bridge this gap, the authors construct a multi-perspective media profiling framework that integrates graph-structured and textual information, proposing a reinforcement learning–based adaptive fusion strategy. They introduce MBFC-2025, a large-scale annotated dataset, and develop the first cross-dataset systematic evaluation benchmark by leveraging graph neural networks and large language models to generate graph structures. The proposed approach achieves state-of-the-art performance on the ACL-2020 benchmark, establishes strong baselines for MBFC-2025, and reveals empirical patterns regarding the effectiveness of different representations and fusion mechanisms in low-resource settings.

Abstract

News outlets shape public opinion at a scale that makes automated detection of political bias and factuality essential. However, the field still lacks unified resources, comprehensive evaluations across diverse approaches, and systematic analyses of the representations and fusion strategies that matter most, especially under label sparsity and dataset diversity. In addition, there is little empirical work reporting broad, observation-driven findings about what consistently works, what fails, and why. We address these gaps through four main contributions. First, we introduce MBFC-2025, a large-scale label set covering approximately 2,600 outlets from Media Bias/Fact Check (MBFC). Second, we construct multiview representations for ACL-2020 (Panayotov et al., 2022), which includes around 900 outlets, as well as for MBFC-2025. These representations span Alexa graphs, hyperlink graphs, LLM-derived graphs, articles, and Wikipedia descriptions. Third, we provide a systematic evaluation and analysis of embedding views and fusion strategies, including a reinforcement learning-based fusion variant. Fourth, we conduct extensive experiments that achieve state-of-the-art results on ACL-2020 and establish strong benchmarks on MBFC-2025.

Problem

• political bias
• factuality
• media profiling
• label sparsity
• dataset diversity

Innovation

• multi-view representation
• media bias detection
• reinforcement learning fusion
• large-scale media profiling
• factuality assessment