Advances in Fake News Detection: A Comprehensive Survey of Methods, Datasets, and Challenges
Year: 2026
Type: conference-paper
Abstract: This paper examines the very serious issue of detecting fake news. The large volume of misinformation on the Internet has made it necessary for developing methods to identify false information on the Internet. Because fake news can be difficult to identify due to language and image manipulation, rapid dissemination of false information, and even through using adversarial attacks to attack or disrupt detection systems; we feel there is a great need for researchers and practitioners to have access to a review of state-of-the-art research in the field of fake news detection methodologies (content-based, context-based, multimodal, hybrid, knowledge-based, and adversarial robustness). We will also categorize the attributes of fake news (textual, visual, social context, temporal, and user-based) so that we may better understand how each attribute improves the performance and interpretability of fake news detection systems. Additionally, we will discuss some of the most common benchmarks and evaluation metrics currently used to compare the effectiveness of fake news detection systems in order to allow for comparative analysis and systematic experimentation by researchers. Finally, we will emphasize the need for the development of future fake news detection systems that are scalable, robust, multilingual, and able to provide real-time detection of false information in order to meet the quickly changing requirements of identifying false information on the internet. By describing current research, identifying potential areas of open problems and suggesting ways to solve those problems, we anticipate our survey to be an important tool in advancing the next generation of fake news detection systems to assist societies in adapting to the ever-changing digital world.
Institution: Bennett University
Language: English
Subfield: Sociology and Political Science
Field: Social Sciences
Domain: Social Sciences
Open Access status: hybrid
OpenAlex ID: W7203636133