Mitigating Media Bias through Neutral Article Generation
This work addresses media bias for readers seeking balanced information, but it is incremental as it builds on existing mitigation methods by focusing on neutral generation rather than just displaying diverse articles.
The authors tackled the problem of media bias by proposing a new task of generating a single neutral article from multiple biased articles, and they introduced a new dataset, evaluation metric, and baselines to establish a foundation for this task.
Media bias can lead to increased political polarization, and thus, the need for automatic mitigation methods is growing. 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. Therefore, 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. In this paper, we compile a new dataset NeuWS, define an automatic evaluation metric, and provide baselines and multiple analyses to serve as a solid starting point for the proposed task. Lastly, we obtain a human evaluation to demonstrate the alignment between our metric and human judgment.