Paper Type
Complete
Abstract
This paper presents a novel human-AI collaborative framework for detecting and mitigating healthcare information disorders in cyberspace. Despite increasing efforts to combat misinformation, current approaches face significant limitations in integration, verification, multilingual capability, and scalability. Our proposed framework addresses these gaps through a three-dimensional evaluation system that assesses source credibility, content quality, and evidence verification across multiple languages. The architecture integrates advanced AI techniques with human judgment through three interconnected subsystems: evidence synthesis using multi-agent large language models, user credibility evaluation employing both automated analysis and community feedback, and a human-AI collaboration interface that optimizes information presentation. This integrated approach enables effective verification processes while reducing cognitive load for users, particularly benefiting vulnerable communities with limited access to reliable healthcare information. The framework offers a scalable solution that balances technological sophistication with human expertise to strengthen information ecosystem resilience.
Paper Number
1184
Recommended Citation
Hong, Lingzi; Chuprov, Sergei; and Wan, Yun, "Mitigating Health Misinformation Through Human-AI Collaboration" (2025). AMCIS 2025 Proceedings. 3.
https://aisel.aisnet.org/amcis2025/social_comput/social_comput/3
Mitigating Health Misinformation Through Human-AI Collaboration
This paper presents a novel human-AI collaborative framework for detecting and mitigating healthcare information disorders in cyberspace. Despite increasing efforts to combat misinformation, current approaches face significant limitations in integration, verification, multilingual capability, and scalability. Our proposed framework addresses these gaps through a three-dimensional evaluation system that assesses source credibility, content quality, and evidence verification across multiple languages. The architecture integrates advanced AI techniques with human judgment through three interconnected subsystems: evidence synthesis using multi-agent large language models, user credibility evaluation employing both automated analysis and community feedback, and a human-AI collaboration interface that optimizes information presentation. This integrated approach enables effective verification processes while reducing cognitive load for users, particularly benefiting vulnerable communities with limited access to reliable healthcare information. The framework offers a scalable solution that balances technological sophistication with human expertise to strengthen information ecosystem resilience.
When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.
Comments
SOCCOMP