Identifying whether online information is faulty or ungrounded is important to ensure information integrity and a well-informed public. This was especially challenging during the COVID-19 pandemic when misinformation spread like wildfire across the Internet. A new project led by Associate Professor Dong Wang will integrate diverse human and machine intelligence to examine multimodal data (e.g., text and image) that was produced during the pandemic. His project, "Crowd-Assisted Human-AI Teaming with Explanations," has been awarded a three-year, $599,999 grant from the National Science Foundation (NSF).
According to Wang, the new project will develop a crowd worker-based interactive artificial intelligence (AI) system that explores the collective strengths of the professional knowledge of domain expert crowd workers, the general logical reasoning ability of non-expert crowd workers, and the effective information retrieval capability of AI models. The researchers will recruit experts in the field, such as healthcare providers, and freelance workers, or average people, from crowdsourcing platforms like Amazon MTurk or Prolific. These crowd workers will perform tasks to help train the AI models, making the system more robust.
"While significant efforts in artificial intelligence and machine learning have addressed information integrity in this type of multimodal setting, many solutions cannot be directly applied due to lack of domain specific knowledge and the expertise needed to provide meaningful, convincing explanations," Wang said.
While the focus of this project is COVID-19, the framework and models that are developed will be able to address information integrity with explanations in other domains, such as healthcare, disaster response, and public safety.
Wang's research interests lie in the areas of human-centered AI, social sensing and intelligence, big data analytics, misinformation detection, and human cyber-physical systems. He holds a PhD in computer science from the University of Illinois Urbana-Champaign.