Fighting Fake News: A Survey of AI-based Models, Frameworks and Challenges

Recently, the rapid growth of digital fake news has gained significant attention in both social media and artificial intelligence (AI) due to fake news can influence daily life deeply. This survey provides a review on AI-based fake news detection (FND), beginning by introducing the theoretical foundations like fake news definition, fake news ecosystem, related terms and fake news characteristics. Then, we introduce a taxonomy that separates AI-based FND methods into two categories which are model-centric models and process-centric frameworks. We then evaluate various model-centric models ranging from traditional models to machine learning, deep learning, and trending models. A significant portion of this work focuses on AI-based FND frameworks, which include dataset, data augmentation, information extraction, model validation and refinement, and results explanation and feedback. Finally, we discuss major challenges and trends to build more reliable information environments.

Authors

Institutions

Publication Details

Journal
ACM Computing Surveys
Published
2026-11-14
DOI
https://doi.org/10.1145/3863938
Primary Topic
Misinformation and Its Impacts
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Fighting Fake News: A Survey of AI-based Models, Frameworks and Challenges

Jimmy Xiangji Huang, Yizheng Huang, Li Zeng
ACM Computing Surveys
Misinformation and Its Impacts
article

Fighting Fake News: A Survey of AI-based Models, Frameworks and Challenges

Jimmy Xiangji Huang, Yizheng Huang, Li Zeng
article en

Abstract

Recently, the rapid growth of digital fake news has gained significant attention in both social media and artificial intelligence (AI) due to fake news can influence daily life deeply. This survey provides a review on AI-based fake news detection (FND), beginning by introducing the theoretical foundations like fake news definition, fake news ecosystem, related terms and fake news characteristics. Then, we introduce a taxonomy that separates AI-based FND methods into two categories which are model-centric models and process-centric frameworks. We then evaluate various model-centric models ranging from traditional models to machine learning, deep learning, and trending models. A significant portion of this work focuses on AI-based FND frameworks, which include dataset, data augmentation, information extraction, model validation and refinement, and results explanation and feedback. Finally, we discuss major challenges and trends to build more reliable information environments.

ACM Computing Surveys
York University (CA), York University (US), University of York (GB)
Misinformation and Its Impacts
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon