Collaborative Research: III: Small: Entity- and Event-driven Media Bias Detection

民主是由舆论塑造的，反过来，公众舆论又受到人们阅读、观看和收听的新闻的显著影响。因此，消息灵通的公众必须了解他们消费的新闻是如何被选择、打包和呈现的。该项目旨在建立计算机系统，以检测和量化媒体意识形态如何在文章及其构成事件一级影响新闻的创作和呈现。该项目将促进新闻生产的透明度，提高公众对媒体决策的认识。开发的工具可以有效和高效地支持在组织和文章层面衡量媒体意识形态，这有助于在包括政治学、社会科学和传播学在内的广泛领域进行研究。拟议的研究将涉及来自不同背景的研究生和本科生，特别是代表性不足的群体。开发的数据集和方法将构成新开发课程中模块的基础。在该项目中产生的知识将通过演示、发布的博客、播客上的演讲和报纸的客座文章向公众传播。这个项目将研究如何通过选择和组织新闻文章中的内容来包装新闻造成的媒体偏见，并开发实体和事件驱动的计算模型来检测意识形态内容选择和预测文章级别的意识形态。将探索三项主要研究任务。首先，建立语篇感知事件分类模型，将主要事件的描述与其他语境告知事件和间接相关事件区分开来。其次，构建实体和事件驱动的情境表征学习框架，通过捕捉实体和事件之间的关系来检测媒体偏见。第三，通过将特定于媒体的语言从意识形态内容中分离出来，研究对抗性学习以预测具有细粒度分数的新闻文章的政治意识形态。这一奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

Democracy is shaped by public opinion, and public opinion in turn is significantly influenced by the news that is read, watched, and listened to. It is thus essential for an informed public to understand how the news they consume is being selected, packaged, and presented. This project aims to build computational systems to detect and quantify how media ideology affects the creation and presentation of news at the level of articles and their constituent events. This project will promote the transparency of news production and enhance public awareness of media decisions. The developed tools can effectively and efficiently support the measurement of media ideology at organization- and article-levels, which facilitates research in broad areas, including political science, social science, and communications. The proposed research will involve graduate and undergraduate students from a diverse array of backgrounds, especially underrepresented groups. The developed datasets and methods will form the basis of modules in newly developed courses. The knowledge produced in the project will be distributed to the public via demos, published blogs, talks at podcasts, and guest essays to newspapers. This project will examine how media bias can result from the packaging of news via the selection and organization of contents presented in news articles, and develop entity- and event-driven computational models for detecting ideological content selection and predicting article-level ideology. Three main research tasks will be explored. First, discourse-aware event categorization models will be developed to distinguish descriptions of main events from other context-informing events and indirectly-related events. Second, an entity- and event-driven contextual representation learning framework will be built to detect media bias by capturing relations between entities and events. Third, adversarial learning will be investigated to predict the political ideology of a news article with a fine-grained score by disentangling media-specific languages from ideological content.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.