Fake Social Media Post Detection by Using Deep Learning Algorithm

Abstract

In today's digital age, social media serves as both a boon and a bane, offering immense opportunities for personal growth while also being a breeding ground for misinformation and deception. The rise of sophisticated multimedia manipulation techniques has blurred the line between reality and fiction, presenting significant challenges to discerning genuine content from fabricated ones. This paper presents an overview of the escalating threat posed by fake posts on social media and proposes a novel approach for their detection. The proposed method leverages advanced technologies such as Error Level Analysis (ELA) and Convolutional Neural Networks (CNNs) to distinguish between authentic and manipulated posts. Unlike traditional approaches reliant on manual feature extraction, our framework employs deep learning methodologies for more nuanced pattern recognition and generalization to unseen data. By combining ELA for initial image analysis and CNNs for deep feature extraction, followed by classification using Support Vector Machines (SVMs) and K-Nearest Neighbors (KNNs), we achieve robust detection of fake images .Experimental results demonstrate the effectiveness of our approach, with a peak accuracy of 91.3% using Residual Networks and KNN. This method offers a promising solution to mitigate the proliferation of fake images on social media platforms, thereby combating the spread of misinformation, propaganda, and chaos.