[论文解读] The Media Bias Taxonomy: A Systematic Literature Review on the Forms and Automated Detection of Media Bias

Timo Spinde, Smilla Hinterreiter+5 more|arXiv (Cornell University)|Dec 26, 2023

Media Influence and Politics被引用 10

一句话总结

本论文提出 Media Bias Taxonomy，并对 3,140 篇关于媒体偏见检测的论文（2019–2022）进行了系统性文献综述，强调 transformer 基于的进展以及跨学科性方面的空缺。

ABSTRACT

The way the media presents events can significantly affect public perception, which in turn can alter people's beliefs and views. Media bias describes a one-sided or polarizing perspective on a topic. This article summarizes the research on computational methods to detect media bias by systematically reviewing 3140 research papers published between 2019 and 2022. To structure our review and support a mutual understanding of bias across research domains, we introduce the Media Bias Taxonomy, which provides a coherent overview of the current state of research on media bias from different perspectives. We show that media bias detection is a highly active research field, in which transformer-based classification approaches have led to significant improvements in recent years. These improvements include higher classification accuracy and the ability to detect more fine-granular types of bias. However, we have identified a lack of interdisciplinarity in existing projects, and a need for more awareness of the various types of media bias to support methodologically thorough performance evaluations of media bias detection systems. Concluding from our analysis, we see the integration of recent machine learning advancements with reliable and diverse bias assessment strategies from other research areas as the most promising area for future research contributions in the field.

研究动机与目标

• 建立统一的 Media Bias Taxonomy，以跨学科方式组织概念和术语。
• 总结计算机科学在媒体偏见检测方面的贡献并对方法进行分类。
• 评估数据集和评估实践，以改进偏见检测系统。
• 识别空缺并提出将机器学习与社会科学视角结合的方向。

提出的方法

• 使用来自 DBLP 和 Semantic Scholar 的自动化、基于关键词的文献检索来收集候选论文。
• 应用人工筛选和多阶段筛选，以识别使用计算机科学方法进行偏见检测的论文。
• 通过整合语言、情境、认知和报道层面的偏见概念，开发并呈现 Media Bias Taxonomy。
• 将计算机科学方法分为六大类，包括传统 NLP、简单 ML、Transformer 与非 Transformer ML、非神经网络，以及基于图的方法。

Figure 1. Number of publications at each step of the literature retrieval and review of computer science publications.

实验结果

研究问题

• RQ1 RQ1：文献中各种偏见形式之间的关系是什么？
• RQ2 RQ2：在自动识别媒体偏见的方法方面有哪些主要进展？
• RQ3 RQ3：哪些 CS 方法在自动识别媒体偏见方面最具前景？
• RQ4 RQ4：社会科学研究如何研究媒体偏见，以及它如何帮助 CS 研究？

主要发现

• 媒体偏见检测是一个高度活跃的领域，基于 transformer 的分类在准确度和更细粒度的偏见检测方面表现更好。
• 现有项目在跨学科性方面存在不足，对偏见类型全谱的认知有限，阻碍了全面评估。
• 需要将最近的 ML 进展与来自其他学科的可靠、多样化偏见评估策略相结合。
• Media Bias Taxonomy 将心理学、语言学和社会学的概念与 CS 方法联系起来，以支持更清晰的评估和比较。

Figure 2. Number of publications at each step of the literature retrieval and review for the Media Bias Taxonomy.