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

TL;DR

This paper introduces new large-scale datasets and multiview representations for analyzing media bias and factuality, along with systematic evaluations of fusion strategies, achieving state-of-the-art results.

Contribution

It provides a comprehensive resource suite, including datasets and multiview representations, and offers empirical analysis of fusion methods for media profiling.

Findings

Multiview representations improve bias detection accuracy.

Reinforcement learning-based fusion enhances performance.

State-of-the-art results on ACL-2020 and strong benchmarks on MBFC-2025.

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.