A systematic review on media bias detection: What is media bias, how it is expressed, and how to detect it
Expert Systems with Applications, vol. 237, pp. 121641, 2024. doi:10.1016/j.eswa.2023.121641
Abstract
Media bias is a pervasive phenomenon that affects the way news is produced and consumed, with significant implications for public opinion and democratic processes. This paper presents a systematic review of the current state of automated media bias detection. We analyze 120+ studies covering how media bias is defined, expressed, and detected. We propose a comprehensive taxonomy of 17 bias types organized across four levels (lexical, sentence, article, and outlet) and survey the datasets, methods, and evaluation approaches used in the field.
Keywords
Media bias detectionNatural Language ProcessingSystematic reviewDisinformationPropaganda
Related work
- A benchmark of expert-level academic questions to assess AI capabilitiesNature, 2026
- Modeling the impact of research data unavailability on scienceJournal of Informetrics, 2026
- Agentic-JEPA: A Self-Supervised World Model for Planning in Text-Based Agent EnvironmentsPreprint, 2026
- Media Bias Bias-Mitigated Dataset (MBBMD): A Hierarchical, Perspectivist, and Counterfactually-Augmented Corpus for Bias Detection in Spanish NewsProcesamiento del Lenguaje Natural (SEPLN) 2026, 2026