Authors

Arya Suneesh, Balasubramanian Palani

Abstract

Fake news on social media platforms poses significant threats to public trust and information integrity. This research explores the application of quantum machine learning (QML) techniques for detecting fake news by leveraging quantum computing’s unique capabilities. Our work introduces a hybrid quantum-classical framework that utilizes quantum convolutional neural networks (QCNNs) with angle and amplitude encoding schemes for processing multimodal features from text and images. Experiments conducted on benchmark datasets - GossipCop and Politifact - demonstrate that our quantum-enhanced model achieves superior performance compared to classical approaches, with accuracy rates of 88.52% and 85.58%, and F1 scores of 93.19% and 90.20% respectively. Our findings establish QML as a viable approach for addressing the challenges of fake news detection in the digital era.

Under Review at the QuantumNLP Workshop at AACL-IJCNLP 2025