DeHiDe: Deep Learning-based Hybrid Model to Detect Fake News using Blockchain

TL;DR

This paper introduces DeHiDe, a hybrid deep learning and blockchain framework designed to improve fake news detection by leveraging blockchain's transparency and deep learning's accuracy, aiming to outperform existing methods.

Contribution

The paper presents a novel hybrid model combining deep learning with blockchain technology for more effective fake news detection, enhancing robustness and accuracy.

Findings

DeHiDe outperforms existing fake news detection methods.

Blockchain integration improves data provenance and traceability.

Deep learning enhances detection accuracy.

Abstract

The surge in the spread of misleading information, lies, propaganda, and false facts, frequently known as fake news, raised questions concerning social media's influence in today's fast-moving democratic society. The widespread and rapid dissemination of fake news cost us in many ways. For example, individual or societal costs by hampering elections integrity, significant economic losses by impacting stock markets, or increases the risk to national security. It is challenging to overcome the spreading of fake news problems in traditional centralized systems. However, Blockchain-- a distributed decentralized technology that ensures data provenance, authenticity, and traceability by providing a transparent, immutable, and verifiable transaction records can help in detecting and contending fake news. This paper proposes a novel hybrid model DeHiDe: Deep Learning-based Hybrid Model to Detect Fake News using Blockchain. The DeHiDe is a blockchain-based framework for legitimate news sharing by filtering out the fake news. It combines the benefit of blockchain with an intelligent deep learning model to reinforce robustness and accuracy in combating fake news's hurdle. It also compares the proposed method to existing state-of-the-art methods. The DeHiDe is expected to outperform state-of-the-art approaches in terms of services, features, and performance.