In Plain Sight: Media Bias Through the Lens of Factual Reporting

By Lisa Fan, M. White, Eva Sharma, Ruisi Su, Prafulla Kumar Choubey, Ruihong Huang, Lu Wang. 2019

129 citations recorded by the source corpus.

The increasing prevalence of political bias in news media calls for greater public awareness of it, as well as robust methods for its detection. While prior work in NLP has primarily focused on the lexical bias captured by linguistic attributes such as word choice and syntax, other types of bias stem from the actual content selected for inclusion in the text. In this work, we investigate the effects of informational bias: factual content that can nevertheless be deployed to sway reader opinion. We first produce a new dataset, BASIL, of 300 news articles annotated with 1,727 bias spans and find evidence that informational bias appears in news articles more frequently than lexical bias. We further study our annotations to observe how informational bias surfaces in news articles by different media outlets. Lastly, a baseline model for informational bias prediction is presented by fine-tuning BERT on our labeled data, indicating the challenges of the task and future directions.

Subfields: General Social Sciences, Sociology and Political Science, Natural Language Processing, AI Ethics, Fairness & Society

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In General Social Sciences

In Sociology and Political Science

In Natural Language Processing

In AI Ethics, Fairness & Society

Citations in the corpus

Queens Are Powerful Too: Mitigating Gender Bias in Dialogue Generation (2019, background): “In particular, they make predictions that directly reﬂect the harmful societal biases present in training datasets, such as racial bias in sports reports (Merullo et al., 2019) and political bias in news data (Fan et al., 2019).”
Perturbation Augmentation for Fairer NLP (2022, background): “There is increasing evidence that models can instantiate social biases (Buolamwini and Gebru, 2018; Stock and Cissé, 2018; Fan et al., 2019; Merullo et al., 2019; Prates et al., 2020), often replicating or amplifying harmful statistical associations in their training data (Caliskan et al., 2017;…”
Gender-Aware Reinflection using Linguistically Enhanced Neural Models (2020, background): “…at a great pace and raised expectation about the quality of results and especially their impact in a social context, including not only race (Merullo et al., 2019) and politics (Fan et al., 2019), but also gender identities (Font and Costa-jussà, 2019; Dinan et al., 2019; Dinan et al., 2020).”