Tracking the Takes and Trajectories of English-Language News Narratives across Trustworthy and Worrisome Websites

Understanding how misleading and outright false information enters and spreads within news ecosystems remains a difficult challenge that requires tracking how stories spread across thousands of fringe and mainstream news websites. To take this challenge, we introduce a novel system that utilizes encoder-based large language models and zero-shot stance detection to scalably identify and track news stories and their attitudes to different topics across thousands of factually unreliable, mixed-reliability, and factually reliable English-language news websites. Deploying our system over an 18-month period, we track the spread of 146K news stories across over 4,000 websites. Using network-based interference via the NETINF algorithm, we show that the paths of news stories and the stances of websites toward particular entities can be used to uncover slanted propaganda networks (e.g., anti-vaccine and anti-Ukraine) and to identify the most influential websites in spreading these attitudes in the broader news ecosystem. We hope that the increased visibility into news ecosystems that our system provides assists with the reporting and fact-checking of propaganda and disinformation.