Analyzing Political Bias and Unfairness in News Articles at Different Levels of Granularity

Chen, Wei-Fan; Khatib, Khalid Al; Wachsmuth, Henning; Stein, Benno

doi:10.18653/v1/2020.nlpcss-1.16

Cited by 25 publications

(29 citation statements)

References 15 publications

(19 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our model, however, sharpens the notions of framing and coverage biases by linking them to strategies at the lexical and discursive level that can be opportunistic and evolve over time. We also see the confirmation of different levels of granularity in our corpus: category-level, message-level and media source level [1,7].…”

Section: Discussionsupporting

confidence: 61%

Examining Linguistic Biases in Telegram with a Game Theoretic Analysis

Höhn

Asher

Mauw

2021

Disinformation in Open Online Media

View full text Add to dashboard Cite

Selective formulations and selective reporting of facts in political news are deliberately used to create particular identities of different political sides. This becomes evident in media dialogue reporting about political conflicts. In contrast to most NLP-based studies of linguistic bias, we engage critically with its nature, aiming at a later de-biasing or at least raising awareness about linguistic bias in political news. We found inspiration in conversation analysis (CA), membership categorisation analysis (MCA) and a game-theoretic approach to discourse called epistemic message exchange (ME) games. We identified three types of bias: selective reports about facts, selective formulations when reporting about the same facts, and different histories built up by the differences in the first two. We extend the epistemic ME games model with findings from a qualitative study.

show abstract

Section: Discussionsupporting

confidence: 61%

Examining Linguistic Biases in Telegram with a Game Theoretic Analysis

Höhn

Asher

Mauw

2021

Disinformation in Open Online Media

View full text Add to dashboard Cite

show abstract

“…To date, only a few research projects focus on the detection and aggregation of bias Spinde et al, 2020c). Even though bias embodies a complex structure, contributions (Hube and Fetahu, 2019;Chen et al, 2020) often neglect annotator background and use crowdsourcing to collect annotations. Therefore, existing data sets exhibit low annotator agreement and inferior quality.…”

Section: Introductionmentioning

confidence: 99%

Neural Media Bias Detection Using Distant Supervision With BABE - Bias Annotations By Experts

Spinde¹,

Plank²,

Krieger³

et al. 2021

Findings of the Association for Computational Linguistics: EMNLP 2021

View full text Add to dashboard Cite

Media coverage has a substantial effect on the public perception of events. Nevertheless, media outlets are often biased. One way to bias news articles is by altering the word choice. The automatic identification of bias by word choice is challenging, primarily due to the lack of a gold standard data set and high context dependencies. This paper presents BABE, a robust and diverse data set created by trained experts, for media bias research. We also analyze why expert labeling is essential within this domain. Our data set offers better annotation quality and higher inter-annotator agreement than existing work. It consists of 3,700 sentences balanced among topics and outlets, containing media bias labels on the word and sentence level. Based on our data, we also introduce a way to detect bias-inducing sentences in news articles automatically. Our best performing BERT-based model is pre-trained on a larger corpus consisting of distant labels. Fine-tuning and evaluating the model on our proposed supervised data set, we achieve a macro F 1 -score of 0.804, outperforming existing methods.

show abstract

“…In recent years, research on different types of bias in natural language has received a considerable amount of attention. Media bias is one prominent example (Fan et al, 2019), particular the political bias of news articles (Chen et al, 2020). In various sub-fields of NLP, studies on media bias are concerned with analyzing techniques utilized by media outlets when reporting news.…”

Section: Related Workmentioning

confidence: 99%

Argument from Old Man's View: Assessing Social Bias in Argumentation

Spliethöver,

Wachsmuth

2020

Preprint

Self Cite

View full text Add to dashboard Cite

Social bias in language -towards genders, ethnicities, ages, and other social groups -poses a problem with ethical impact for many NLP applications. Recent research has shown that machine learning models trained on respective data may not only adopt, but even amplify the bias. So far, however, little attention has been paid to bias in computational argumentation. In this paper, we study the existence of social biases in large English debate portals. In particular, we train word embedding models on portal-specific corpora and systematically evaluate their bias using WEAT, an existing metric to measure bias in word embeddings. In a word co-occurrence analysis, we then investigate causes of bias. The results suggest that all tested debate corpora contain unbalanced and biased data, mostly in favor of male people with European-American names. Our empirical insights contribute towards an understanding of bias in argumentative data sources.

show abstract

Analyzing Political Bias and Unfairness in News Articles at Different Levels of Granularity

Cited by 25 publications

References 15 publications

Examining Linguistic Biases in Telegram with a Game Theoretic Analysis

Examining Linguistic Biases in Telegram with a Game Theoretic Analysis

Neural Media Bias Detection Using Distant Supervision With BABE - Bias Annotations By Experts

Argument from Old Man's View: Assessing Social Bias in Argumentation

Contact Info

Product

Resources

About