Machine-learning media bias

D'Alonzo, Samantha; Tegmark, Max

doi:10.1371/journal.pone.0271947

Cited by 12 publications

(7 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a survey experiment, respondents enjoy complete information about the outcomes of unilateral actions. In reality, partisan media spin and filter political news for the general public, making it difficult to access unbiased information on unilateral actions (D'Alonzo and Tegmark 2022;Guo, Ma and Vosoughi 2022;Iyengar and Kinder 2010).…”

Section: Discussionmentioning

confidence: 99%

“…or failure is known. Given the highly polarized nature of U.S. news media (Guo, Ma, and Vosoughi 2022;Iyengar and Kinder 2010;D'Alonzo and Tegmark 2022), acquiring unbiased information about policy success is especially difficult. As a result, we argue, our findings cannot rule out the possibility the public check on presidential unilateralism may make citizens worse off as presidents issue unilateral actions that they never intend to fully implement.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Public Responses to Unilateral Policymaking

Goehring,

Lowande

2024

J Exp Polit Sci

View full text Add to dashboard Cite

Presidents possess vast authority over policies and outcomes. Recent studies suggest the public checks this unilateralism through expressive opinions and political participation. We reevaluate this accountability link with a preregistered panel survey that incorporates a number of design and conceptual improvements over existing experimental studies. Our findings reveal a more complex relationship between presidential actions and public opinion. We find no evidence that the public reacts negatively to unilateralism – and some evidence they react positively. Respondents, however, may punish an incumbent for failing to implement the proposed policy change. While such a result suggests that the public can hold presidents accountable, we close by discussing how a lack of information likely renders this check moot.

show abstract

Section: Discussionmentioning

confidence: 99%

mentioning

confidence: 99%

Public Responses to Unilateral Policymaking

Goehring,

Lowande

2024

J Exp Polit Sci

View full text Add to dashboard Cite

show abstract

“…Finally, there is the bias introduced by the actual words and writing style used, or the writing style bias. Writing style bias is the the word choice -or lexical bias -and framing biases in the text; a news piece can be biased by both the words, or phrases, it chooses to use as well as the context of keywords in the text [21], [22].…”

Section: Natural Language Understanding and Media Biasmentioning

confidence: 99%

Developing a Natural Language Understanding Model to Characterize Cable News Bias

Benson,

Cruickshank

2024

IEEE Access

View full text Add to dashboard Cite

Media bias has been extensively studied by both social and computational sciences. However, current work still has a large reliance on human input and subjective assessment to label biases. This is especially true for cable news, which has a continued presence in American media but a lack of textbased bias identification in research. To address these issues, we develop an unsupervised machine learning method to characterize the bias of cable news programs without any human input. This method relies on the analysis of what topics are mentioned through Named Entity Recognition and how those topics are discussed through Stance Analysis in order to cluster programs with similar biases together. Applying our method to 2020 cable news transcripts, we find that cable news programs tend to cluster together consistently over time and roughly correspond to the cable news network of the program. This method reveals the potential for future tools to more objectively assess media bias and characterize unfamiliar media environments, and the empirical results insight into the nature of bias in American cable news programs.

show abstract

“…Many datasets have been designed to study political bias at different granularity levels: news sources [22], [23], articles [24], paragraphs [25], sentences [26], [27], and headlines [6] with one or more bias types [28].…”

Section: A Datasetsmentioning

confidence: 99%

An Inferential Commonsense-Driven Framework for Predicting Political Bias in News Headlines

2023

View full text Add to dashboard Cite

Identifying political bias in news headlines holds significant importance as it influences the dissemination and consumption of news stories. However, employing conventional methods to do so poses a formidable challenge, as the short headline text is often complex and lacks sufficient syntactic and semantic context. Existing approaches fail to acknowledge the potential of commonsense reasoning in facilitating text comprehension, although it has been shown to aid numerous downstream applications. To this end, to facilitate comprehension and compensate for the lack of context, we propose leveraging inferential commonsense knowledge to simplify, interpret, and explain events that are not explicitly stated in headlines. Furthermore, to fully utilise its potential and deal with the unnecessary noise it may introduce, we present a method for emphasising significant inferences. Using this knowledge, we introduce a novel framework, IC-BAIT, short for Inferential Commonsense aware BiAs IdenTifier, which is a flexible neural network framework designed to enhance political bias prediction in news headlines. We also present two bias-annotated datasets: MediaBias and GoodNews. Experiments on both datasets demonstrate that IC-BAIT significantly enhances the performance of the baseline models used in the framework. Experiments on the datasets show that IC-BAIT improves the baseline models in terms of accuracy (2.0-10.0%), macro-averaged F 1 (2.2-22.2%), Jaccard-score (up to 15.1%), and micro-averaged F 1 (up to 18.6%). Our in-depth qualitative analysis reveals the scenarios in which the selected knowledge is beneficial and when it is detrimental. Datasets and scripts are available at https://github.com/Swati17293/IC-BAIT.

show abstract

Machine-learning media bias

Cited by 12 publications

References 16 publications

Public Responses to Unilateral Policymaking

Public Responses to Unilateral Policymaking

Developing a Natural Language Understanding Model to Characterize Cable News Bias

An Inferential Commonsense-Driven Framework for Predicting Political Bias in News Headlines

Contact Info

Product

Resources

About