Intelligent Evidence-Aware Fake News Detection using NLP and Cybersecurity Analytics

Abstract

The tremendous growth of social media facilitated the rapid dissemination of information, but it has also accelerated the dissemination of fake news and misleading content. The trustworthiness of supporting evidence or cybersecurity-related signals connected to online content may not be sufficiently taken into account by traditional fake news detection techniques, which frequently concentrate exclusively on textual patterns. This study proposes IEFN-CS (Intelligent Evidence-Aware Fake News Detection) that makes use of cybersecurity analytics and natural language processing (NLP) framework for detecting potential false information in social media environments. The suggested framework is produced and evaluated using accessible to the public, the Kaggle fake-news dataset includes content that has been identified as either fake or real. The framework is designed to analyze social-media content and extract contextual and semantic information. The proposed technique employs Natural Language Processing (NLP) and semantic representation is to examine the meaning and credibility-related characteristics of the content. The framework also includes cybersecurity analytics to examine suspicious URLs, source-related traits, and unusual content-sharing habits, as well as evidence-aware analysis to find supporting or contradicting material. These heterogeneous signals are integrated through an evidence-aware decision to classify content as misleading or fake. The performance of the proposed framework is evaluated using accuracy, precision, recall, F1-score. The proposed IEFN-CS framework aims to provide reliable, evidence-supported, and security-aware fake news detection while improving the transparency and robustness of misinformation identification in dynamic social media environments.