Collaborative Research: SaTC: CORE: Small: Targeting Challenges in Computational Disinformation Research to Enhance Attribution, Detection, and Explanation

社交媒体的使用加快了信息共享和即时交流。进入社交媒体的低门槛使更多用户能够参与，并使他们的参与度更长，从而激励有隐藏议程的个人在网上传播虚假信息，以操纵信息和影响意见。虚假新闻、恶作剧和阴谋论等虚假信息越来越成为阻碍在线社交媒体作为可信信息有效渠道发挥作用的因素。故意捏造的虚假信息被武器化，以分裂人们并造成有害的社会影响的案件正在出现。因此，考虑到对信息的需要和安全与防止虚假信息之间的紧张关系，必须理解虚假信息并系统地研究如何提高对虚假信息的抵抗力。该项目旨在研究虚假信息的科学基础，并开发一个计算框架来确定、检测和解释虚假信息，以便为决策提供信息。该项目涉及通过开发新的知识和系统的计算框架来从根本上改变打击虚假信息的过程，以解决检测在线虚假信息的主要挑战(来源、数据和可解释性)。开发的技术结合了跨学科理论和计算算法，以帮助政策制定者和社交媒体用户处理虚假信息。项目成果有助于推进对虚假信息的最先进研究，并引入基于风格和基于图形的优化方法，可以确定虚假信息的来源及其特征，通过利用多模式数据和高级社会背景关系来进行虚假信息检测，需要最少数据或监督的虚假信息检测方法，以及依赖于成熟的心理学和认知理论的可解释检测技术，并使人类互动能够增强检测和解释。更广泛地说，该项目对数据挖掘、机器学习、图挖掘和文本挖掘研究以及传播和新闻领域关于可信度、透明度和减少虚假信息的社会科学研究做出了贡献。该奖项反映了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。

The use of social media has accelerated information sharing and instantaneous communications. The low barrier to entering social media enables more users to participate and keeps them engaged longer, incentivizing individuals with a hidden agenda to spread disinformation online to manipulate information and sway opinion. Disinformation, such as fake news, hoaxes, and conspiracy theories, has increasingly become a hindrance to the functioning of online social media as an effective channel for trustworthy information. Cases are emerging where deliberately fabricated disinformation is weaponized to divide people and create detrimental societal effects. Therefore, it is imperative to understand disinformation and systematically investigate how to improve resistance against it, considering the tension between the need for information and security and protection from disinformation. The project aims to study the scientific underpinnings of disinformation and develop a computational framework to attribute, detect, and explain disinformation to inform policymaking. The project involves fundamentally transforming the process to combat disinformation by developing new knowledge and a systematic computational framework to address major (provenance, data, and explanaibility) challenges of detecting online disinformation. The techniques developed combine interdisciplinary theories and computational algorithms to help policymakers and social media users address disinformation. The project outcomes help advance state-of-the-art research on disinformation and introduce style-based and graph-based optimization methods that can determine the source of disinformation and its characteristics, disinformation detection methods requiring minimal data or supervision by harnessing multimodal data and high-level social context relations, and interpretable detection techniques that rely on well-established psychological and cognitive theories, and enable human interactions to enhance detection and explanation. More broadly, the project contributes to data mining, machine learning, graph mining, and text mining research as well social science research in communication and journalism on credibility, transparency, and disinformation mitigation.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.