Fake News Detection via Textual BERT Embeddings and Knowledge-Aware Graph Neural Networks

Abstract

Fake news generation and propagation is a huge challenge of the digital era, resulting in different social impacts, namely bandwagon, validity content, and deceiving the public with spam and much more. The rapid spread of fake news not only fosters misinformation but also degrades the credibility of news sources. To comprehend the critical need for addressing this persuasive issue, this research presents a framework for detecting fake news using a knowledge-based approach by combining GCN and GNN only for text data. An automatic fact-checking process is applied using concepts like information retrieval, NLP, and Graph theory. The knowledge base is generated using a Twitter dataset, which contains. These attributes serve as pivotal indicators for the development of a knowledge base, subsequently employed to detect prevalent patterns and traits linked to deceptive or false information. We have employed Named Entity Recognition (NER) model to extract SPO triples and Latent Dirichlet Allocation (LDA) for topic modeling, thereby contributing to knowledge base generation. To evaluate the efficacy and efficiency of our proposed model, we utilize deep learning algorithms like GPT-3 and BERT Transformer, providing an acceptable level of accuracy. This research paper delivers valuable insights into addressing the proliferation of fake news on Twitter.