NeuS: Neutral Multi-News Summarization for Mitigating Framing Bias

• URL: http://arxiv.org/abs/2204.04902v1
• Date: Mon, 11 Apr 2022 07:06:01 GMT
• Title: NeuS: Neutral Multi-News Summarization for Mitigating Framing Bias
• Authors: Nayeon Lee, Yejin Bang, Tiezheng Yu, Andrea Madotto, Pascale Fung
• Abstract summary: We propose a new task, a neutral summary generation from multiple news headlines of the varying political spectrum. One of the most interesting observations is that generation models can hallucinate not only factually inaccurate or unverifiable content, but also politically biased content.
• Score: 54.89737992911079
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Media framing bias can lead to increased political polarization, and thus, the need for automatic mitigation methods is growing. We propose a new task, a neutral summary generation from multiple news headlines of the varying political spectrum, to facilitate balanced and unbiased news reading. In this paper, we first collect a new dataset, obtain some insights about framing bias through a case study, and propose a new effective metric and models for the task. Lastly, we conduct experimental analyses to provide insights about remaining challenges and future directions. One of the most interesting observations is that generation models can hallucinate not only factually inaccurate or unverifiable content, but also politically biased content.

Related papers

• P^3SUM: Preserving Author's Perspective in News Summarization with Diffusion Language Models [57.571395694391654]
  We find that existing approaches alter the political opinions and stances of news articles in more than 50% of summaries. We propose P3SUM, a diffusion model-based summarization approach controlled by political perspective classifiers. Experiments on three news summarization datasets demonstrate that P3SUM outperforms state-of-the-art summarization systems.
  arXiv  Detail & Related papers  (2023-11-16T10:14:28Z)
• Towards Corpus-Scale Discovery of Selection Biases in News Coverage: Comparing What Sources Say About Entities as a Start [65.28355014154549]
  This paper investigates the challenges of building scalable NLP systems for discovering patterns of media selection biases directly from news content in massive-scale news corpora. We show the capabilities of the framework through a case study on NELA-2020, a corpus of 1.8M news articles in English from 519 news sources worldwide.
  arXiv  Detail & Related papers  (2023-04-06T23:36:45Z)
• Unveiling the Hidden Agenda: Biases in News Reporting and Consumption [59.55900146668931]
  We build a six-year dataset on the Italian vaccine debate and adopt a Bayesian latent space model to identify narrative and selection biases. We found a nonlinear relationship between biases and engagement, with higher engagement for extreme positions. Analysis of news consumption on Twitter reveals common audiences among news outlets with similar ideological positions.
  arXiv  Detail & Related papers  (2023-01-14T18:58:42Z)
• Demoting the Lead Bias in News Summarization via Alternating Adversarial Learning [7.678864239473703]
  In news articles the lead bias is a common phenomenon that usually dominates the learning signals for neural extractive summarizers. We introduce a novel technique to demote lead bias and make the summarizer focus more on the content semantics.
  arXiv  Detail & Related papers  (2021-05-29T07:40:59Z)
• Enabling News Consumers to View and Understand Biased News Coverage: A Study on the Perception and Visualization of Media Bias [7.092487352312782]
  We create three manually annotated datasets and test varying visualization strategies. Results show no strong effects of becoming aware of the bias of the treatment groups compared to the control group. Using a multilevel model, we find that perceived journalist bias is significantly related to perceived political extremeness and impartiality of the article.
  arXiv  Detail & Related papers  (2021-05-20T10:16:54Z)
• Mundus vult decipi, ergo decipiatur: Visual Communication of Uncertainty in Election Polls [56.8172499765118]
  We discuss potential sources of bias in nowcasting and forecasting. Concepts are presented to attenuate the issue of falsely perceived accuracy. One key idea is the use of Probabilities of Events instead of party shares.
  arXiv  Detail & Related papers  (2021-04-28T07:02:24Z)
• Mitigating Media Bias through Neutral Article Generation [39.29914845102368]
  Existing mitigation work displays articles from multiple news outlets to provide diverse news coverage, but without neutralizing the bias inherent in each of the displayed articles. We propose a new task, a single neutralized article generation out of multiple biased articles, to facilitate more efficient access to balanced and unbiased information.
  arXiv  Detail & Related papers  (2021-04-01T08:37:26Z)
• Analyzing Political Bias and Unfairness in News Articles at Different Levels of Granularity [35.19976910093135]
  The research presented in this paper addresses not only the automatic detection of bias but goes one step further in that it explores how political bias and unfairness are manifested linguistically. We utilize a new corpus of 6964 news articles with labels derived from adfontesmedia.com and develop a neural model for bias assessment.
  arXiv  Detail & Related papers  (2020-10-20T22:25:00Z)
• We Can Detect Your Bias: Predicting the Political Ideology of News Articles [35.761722515882646]
  We release a dataset of 34,737 articles that were manually annotated for political ideology. We use a challenging experimental setup where the test examples come from media that were not seen during training. Our experimental results show very sizable improvements over using state-of-the-art pre-trained Transformers.
  arXiv  Detail & Related papers  (2020-10-11T20:27:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.