The rapid dissemination of fake news through online news platforms and social media has become a major challenge, significantly influencing public opinion, political decision-making, and social stability. Recent fake news detection methods have achieved promising performance using deep contextual language models such as Bidirectional Encoder Representations from Transformers (BERT). However, most existing approaches process news articles independently and primarily focus on textual semantics while overlooking structural relationships among related news articles. Consequently, valuable graph-based information, including semantic similarity, shared entities, common publishers, and topical relationships, remains underutilized. This paper proposes GraphBERT4FakeNews, a graph transformer framework that jointly learns contextual semantic representations and graph structural information for English fake news detection. First, BERT generates contextualized embeddings from news articles. A news graph is then constructed by connecting semantically related articles according to contextual similarity. Subsequently, a GraphBERT encoder performs graph-aware self-attention to capture both local and long-range structural dependencies without relying on conventional graph convolution operations. Finally, a classification layer predicts whether a news article is genuine or fake. The proposed framework is evaluated on the publicly available FakeNewsNet benchmark, including the GossipCop and PolitiFact datasets. Experimental results demonstrate that GraphBERT4FakeNews effectively integrates semantic understanding with graph structural reasoning, leading to improved fake news detection performance compared with conventional language models and graph neural network approaches.

This study aims to (1) examine the effectiveness of the Convolutional Gated Recurrent Network for Fake News Detection (CGRN4FakeNews) model in fake news classification and (2) compare its performance with baseline methods across different datasets. The model was evaluated using the PolitiFact and GossipCop subsets of the FakeNewsNet dataset. The research process involved text preprocessing and data cleaning, including word tokenization, lowercasing, the removal of URLs, HTML tags, numerical values, punctuation marks, and redundant whitespace, as well as stopword handling. The processed text data were then transformed into vector representations using a word embedding technique for model training and evaluation. The model performance was assessed based on Accuracy, Precision, Recall, F1-score, and Confusion Matrix metrics. The experimental results indicate that the proposed CGRN4FakeNews model effectively distinguishes between real and fake news articles, achieving classification accuracies of 95.75% on the PolitiFact dataset and 91.12% on the GossipCop dataset. These findings demonstrate the effectiveness and suitability of the CGRN4FakeNews model for fake news detection tasks.