RAPID: Countering COVID-19 Misinformation via Situation-Aware Visually Informed Treatment

随着新冠肺炎疫情的蔓延，世界各国和城市纷纷采取隔离、区域封锁等严格措施。越来越多的孤立，加上恐慌和焦虑，给打击错误信息带来了挑战——人们越来越多地利用他们已经熟悉的在线信息来源，而获取替代新闻的机会越来越少。该项目将开发基于文本和图像分析、社会心理学和众包的机制，可在当前的COVID-19危机期间及以后及时用于打击错误信息。该方法的一个新颖之处在于，它通过众包真实图像来应对错误信息的特定实例。这项研究将有助于科学地理解错误信息和有说服力的叙事结构，评估错误信息传播的风险，以及制定对抗错误信息的机制。这个项目的技术目标分为三个重点。第一个重点将调查多模式社交媒体帖子的哪些信息内容和特定部分（例如，一段文字，带有图像的文本，嵌入口号的图像）将得到更强烈的回应，从而增加帖子被分享的可能性。第二个重点是创建指标，根据从用户接触的内容中获得的预测指标，评估错误信息传播的可能性。第三个重点将集中在开发一个系统，以根据公民记者的实地调查和机器学习技术的投入来打击错误信息。最后，该系统将通过调查研究和访谈来评估，以检查系统的可用性，有用性和有效性，以减少错误信息的传播和影响。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

As the COVID-19 pandemic spreads, countries and cities around the globe have taken stringent measures including quarantine and regional lockdown. The increasing isolation, along with the panic and anxiety, creates challenges for countering misinformation--people are increasingly tapping into online information sources already familiar to them with declining chances of accessing alternative stories. This project will develop mechanisms based on text and image analysis, social psychology, and crowd-sourcing that can be used in a timely manner to counter misinformation during the ongoing COVID-19 crisis and beyond. One of the novel features of the approach is to deal with a specific instance of misinformation by crowd-sourcing authentic images that counter this misinformation. This research will contribute to the scientific understanding of misinformation and of persuasive narrative construction, to the assessment of risk for the spread of misinformation, and to the development of mechanisms to counter misinformation. The technical aims of this project are divided into three thrusts. The first thrust will investigate what information content and which specific part of a multimodal social media post (e.g, a piece of text, text with an image, image with an embedded slogan) will receive stronger responses and hence increase the likelihood of the post being shared. The second thrust will create metrics to assess the likelihood of the spread of misinformation based on predictors learned from the content to which users are exposed. The third thrust will focus on the development of a system to counter misinformation based on citizen journalists’ inputs of field investigations and on machine learning techniques. Finally, the system will be evaluated by survey studies and interviews to examine the system’s usability, usefulness, and effectiveness in reducing the spreading and impact of misinformation.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.