Gooi, Hayden (2025) Fake news detection using perceptual hashing algorithms and multimodal logistic regression within a blockchain system. Masters thesis, York St John University.

Preview

Text (MSc by Research thesis) Fake news detection using perceptual hashing algorithms and multimodal logistic regression within a blockchain system.pdf - Published Version Available under License Creative Commons Attribution. Download (1MB) | Preview

Abstract

The rise of fake news poses a significant challenge to public trust in digital media and social media sites. This study presents a novel system for detecting fake news by combining perceptual hashing and blockchain technology to classify articles. The proposed solution stores hashes of news articles on a blockchain to ensure data integrity and immutability. To determine whether a user-submitted article is fake, the system compares its perceptual hash against the stored hashes using Hamming distance and employs a multinomial logistic regression model to classify the article as either real, fake, opinion or partially true. The system's performance is evaluated and compared to existing solutions using metrics such as accuracy, precision, recall, and F1 score, which highlights its efficiency in detecting fake news. Experimental results provided a high system accuracy of 70.25% in identifying fake news. Additionally, the paper addresses the limitations and potential threats that would affect the performance of the solution as well as potential future work and improvements that can be added to mitigate the specified issues, which means that there is potential for this concept to become a reliable tool for fact-checking in the digital age.

Item Type:	Thesis (Masters)
Status:	Published
Subjects:	T Technology > T Technology (General)
School/Department:	School of Science, Technology and Health
URI:	https://ray.yorksj.ac.uk/id/eprint/12548

University Staff: Request a correction | RaY Editors: Update this record