Identifying biases in news using models of narrative framing

这个项目旨在开发工具来检测新闻故事中的偏颇叙述和片面框架，使用新颖的自然语言处理方法来更深入地理解文本。与过度依赖表层词语共现模式的现有方法不同，新方法将能够以更整体和直观的方式捕捉叙事。预期的结果包括以理论为基础的新建模技术，以及一种通过对不同系列新闻文章的推荐来突出偏见的工具。通过提高人们对有偏见的新闻报道的认识，该项目将通过更平衡地公开谈论气候变化和卫生流行病等全球挑战，使澳大利亚人受益。

This project aims to develop tools to detect biased narratives and one-sided framing in news stories using novel natural language processing methods to understand the text more deeply. Unlike existing methods, which overly rely on surface word co-occurrences patterns, the novel methods will be able to capture narratives in a more holistic and intuitive manner. Expected outcomes include new modeling techniques grounded in theory and a tool to highlight biases with recommendations for diverse sets of news articles. By raising awareness to biased news reporting, the project will benefit Australians through more balanced public discourse on global challenges, such as climate change and health pandemics.