Social Media and Fake News Detection using Adversarial Collaboration

Abstract

The diffusion of fake information on social media networks obscures public perception of events, news, and relevant content. Intentional misleading news may promote negative online experiences and influence societal behavioral changes such as increased anxiety, loneliness, and inadequacy. Adversarial attacks target creating misinformation in online information systems. This behavior can be viewed as an instrument to manipulate the online social media networks for cultural, social, economic, and political gains. A method to test a deep learning model-long short-term memory (LSTM) using adversarial examples generated from a transformer model has been presented. The paper attempts to examine features in machine learning algorithms that propagate fake news. Another goal is to evaluate and compare the usefulness of generative adversarial networks with long-term short-term recurrent neural network algorithms in identifying fake news. A closer look at the mechanisms of implementing adversarial attacks in social media systems helps build robust intelligent systems that can withstand future vulnerabilities.

Stylometric Fake News Detection Based on Natural Language Processing Using Named Entity Recognition: In-Domain and Cross-Domain Analysis

“…By analyzing linguistic patterns, syntactic structures, semantic relationships, cultural references, and temporal dependencies through NER techniques, we can better distinguish between factual information and fabricated claims through the NER-SA model to improve the accuracy of detection. Moreover, fake news producers often employ adversarial strategies to evade detection algorithms [34]. In this study, we have made progress in developing defenses against adversarial attacks, such as incorporating robust linguistic features and interpretable models with NER techniques that can identify subtle linguistic manipulations and improve the robustness of NLP approaches.…”