Disability misinformation on Facebook: a comparison of LLM-based fact-checking tools
Information Research an international electronic journal · 20.03.2026 · 31 (iConf) · 1042-1053
DOI: 10.47989/ir31iconf64259 ↗Kurz gefasst
Fachartikel in der Zeitschrift Information Research an international electronic journal, online erschienen am 20.03.2026. Verfasst von Ian Prazak und 4 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Introduction
Social media has become a prominent space for seeking and sharing information, but it also enables misinformation to spread. When it comes to disability-related information, such as how to apply for a Medicaid waiver, understanding the prevalence of false information on social media becomes further complicated due to varying content types. To provide an initial exploration of this problem space, we investigated misinformation propensity within disability-related Facebook groups, group factors associated with it, and the performance of AI fact-checking tools in detecting this type of information.
Method
We identified target Facebook groups through a large-scale survey. From 20 public Facebook groups mentioned in the survey, we scraped 1,407 informational and fact-checkable posts. GPT-4o, GPTo1, and Originality.ai were used to classify the posts and compared. Analysis. The results were validated against the ground-truths generated manually, providing benchmarks for assessing AI tools in detecting misinformation on Facebook.
Results
Our findings reveal that groups centered on developmental disabilities tend to be more vulnerable to misinformation. AI factchecking tools are generally effective in classifying accurate information but presented varying performance in detecting misinformation.
Conclusion
This work provides an initial assessment of the prevalence of misinformation about disability services and the performance of LLM-based tools.
Zitieren
APA
Prazak, I., Padovani, L., Lim, Y., Hsu, J. H., & Lee, M. (2026). Disability misinformation on Facebook: a comparison of LLM-based fact-checking tools. Information Research an international electronic journal, 31(iConf), 1042-1053. https://doi.org/10.47989/ir31iconf64259
Vancouver
Prazak I, Padovani L, Lim Y, Hsu JH, Lee M. Disability misinformation on Facebook: a comparison of LLM-based fact-checking tools. Information Research an international electronic journal. 2026;31(iConf):1042-1053. doi:10.47989/ir31iconf64259
BibTeX
@article{Prazak2026,
author = {Prazak, Ian and Padovani, Leah and Lim, Yool and Hsu, Julia (Hsin-Ping) and Lee, Myeong},
title = {Disability misinformation on Facebook: a comparison of LLM-based fact-checking tools},
journal = {Information Research an international electronic journal},
year = {2026},
volume = {31},
number = {iConf},
pages = {1042--1053},
doi = {10.47989/ir31iconf64259}
}
EUVIMED