Members of Associate Professor Dong Wang's research group, the Social Sensing and Intelligence Lab, will present their research at the Web Conference 2024, which will be held from May 13-17 in Singapore. The Web Conference is the premier venue to present and discuss progress in research, development, standards, and applications of topics related to the Web.
Teaching Assistant Professor Yang Zhang will present the paper, "SymLearn: A Symbiotic Crowd-AI Collective Learning Framework to Web-based Healthcare Policy Adherence Assessment." SymLearn is a novel framework that combines crowdsourcing and AI to assess public adherence to healthcare policies like mask-wearing during events like COVID-19. The key innovation is establishing a mutually beneficial relationship between crowd workers and AI models. While AI rapidly analyzes social media data, humans can fix AI errors, and AI can guide humans to subtle visual details. Insights from SymLearn highlight frontiers in human-AI collective intelligence systems.
PhD student Lanyu Shang will present the paper, "MMAdapt: A Knowledge-Guided Multi-Source Multi-Class Domain Adaptive Framework for Early Health Misinformation Detection." In this paper, Shang and her collaborators propose a novel AI framework called MMAdapt that can detect misinformation related to new and emerging health issues at an early stage. MMAdapt leverages resources from well-studied health domains like cancer and COVID-19 to identify misinformation in new emergent areas like the 2022 Mpox outbreak. It can discern not just false claims, but partially misleading content containing a mixture of accurate and inaccurate statements that can be even more convincing to the public. The researchers aim to enable timely interventions by platforms and agencies when new public health issues arise.
The primary research focus of the Social Sensing and Intelligence Lab lies in the emerging area of human-centered AI, AI for social good, and cyber-physical systems in social spaces. The lab develops interdisciplinary theories, techniques, and tools for fundamentally understanding, modeling, and evaluating human-centered computing and information (HCCI) systems, and for accurately reconstructing the correct "state of the world," both physical and social.