BiaSeer: A Visual Analytics System for Identifying and Understanding Media Bias

Media bias refers to bias in news reporting and coverage, which exists pervasively. By identifying media bias, social scientists can understand different perspectives held by media outlets in news reporting. Existing studies only focus on the media bias analysis of isolated incidents but neglect its sustained characteristics. Thus, they cannot provide a comprehensive understanding of specific news topics. We develop BiaSeer, a visual analytics system for identifying and understanding sustained bias of media outlets. BiaSeer employs an overview-to-detail approach for interactive identification of media bias. The overview assists users in determining the analysis scope of media outlets. It further visualizes the variances in coverage patterns among selected media outlets using a matrix visualization to facilitate the identification of biased news articles. BiaSeer visualizes the sustained bias in the context of event evolution. It first summarizes news articles into events based on a keyword co-occurrence graph and then connects events into a narrative structure using a path-aware story tree construction method. In addition, BiaSeer integrates a sustained bias computation algorithm and enables analysts to compare the narrative structures of different media outlets using the juxtaposition-based visualization approach. We conduct a user experiment to validate the effectiveness of BiaSeer in assisting social scientists in understanding news topics and the usability of the visualization designs. To examine the effectiveness of BiaSeer, we conducted a case study with social scientists on the topics of the Russia-Ukraine conflict. The results demonstrate the utility and usability of BiaSeer in efficiently analyzing media bias and attaining a well-rounded comprehension of news topics.