Unveiling Deception: A GAN-Based Unsupervised Learning Approach for Real-Time Generation and Detection of Text-Based Fake News
Main Article Content
Abstract
Generative artificial intelligence technology advancements have made it easy to generate fake news. Online community platforms like social media have made propagation of such fake news faster and more convenient. We have witnessed the social impact of such fake news in the past few years. In the literature, a Generative Adversarial Network (GAN) is used to detect text-based fake news based on structured data with the supervised learning approaches. However, we have observed that most large-scale online data are unstructured and can not be used with the supervised learning approaches. In this paper, we have used an auto-encoder to select the features from the unstructured data and feed them to GAN.
Article Details
This work is licensed under a Creative Commons Attribution-NoDerivatives 4.0 International License.