This National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) federal grant award (CFDA 47.070) provides $599,999 to the University of Illinois to develop a human-centered AI framework for assessing information integrity, particularly in the context of the COVID-19 pandemic. The project will integrate AI, crowdsourcing, machine learning, and human-AI interactions to: 1) construct a multimodal COVID-19 knowledge graph, 2) leverage both expert and non-expert crowd workers to validate and expand the knowledge graph, and 3) develop a dynamic graph-attentive knowledge discriminator to detect and explain issues with information integrity using natural language descriptions. The goal is to provide accurate assessments of COVID-19 information while generating convincing explanations, leveraging the collective strengths of human and machine intelligence. The award period is from August 2024 to July 2027, and the project is expected to deliver innovative solutions with potential applications beyond the COVID-19 domain.
Generated 1/28/25, 10:07 AM