TL;DR
The proposed model, Crossbred Analogous Tree-Knowledge Deep (CAT-KD), is composed of five key components for comprehensive sentiment analysis and achieves an accuracy of 94.83% and an F1-score of 94.12%, outperforming baseline models with improvements of up to 0.62% in accuracy and 2.46% in F1-score on Twitter datasets.
Results highlight the value of integrating relational graph structures with complementary feature representations for misinformation detection, and provide a foundation for future extensions, including federated learning, explainability techniques, and cross-domain applications in multilingual contexts.
The spreading of fake news via online social media has emerged as one of the major issues in the modern information systems. The existing fake news detection techniques mainly rely on text-based classification methods and are ineffective in incorporating multimodal features, which can be used for fake news detection and classification. This study proposes HGAT-BERT, where a pretrained BERT-Large encoder is coupled with a Heterogeneous Graph Attention Network (HGAT) to learn joint representations for textual, social network and external knowledge graph features. Cross-modal attention and gated residual connections facilitate the integration of these heterogeneous feature streams into a unified representation. On the FakeNewsNet dataset split on PolitiFact and GossipCop data, the research reports an accuracy of 93.7% and an F1 score of 93.2%, an improvement of around 3.5% over the existing methods. The ablation analysis shows that all components represent meaningful contributions to the overall model performance, with cross-modal attention being responsible for the largest marginal contribution.
The Syntactic-optimal Transport Graph Network (SOT-Graph) is proposed, a model that jointly integrates structural and distributional signals and outperforms existing baselines by a margin of 1.30% Macro-F1 on Laptop14 and 1.01% on Twitter.
An innovative model which combines transformer-based context embedding, BiLSTM for capturing of sentiment flows, and GAT for examining relational data is introduced which incorporates contextual, sequential and relational modelling of multilingual opinion mining.
The present study proposes such a multimodal sentiment analysis framework with attention-enhanced properties, a combination of ResNet50 and Convolutional Block Attention Module (CBAM), a textual encoder with BERT, and refinement of relational features via Graph Neural Networks (GNN). The model is designed to address the vulnerability of uni-modal sentiment analysis and integrate related visual and textual evidence. CBAM enhances the visual feature representation with the assistance of channel and spatial attention, but BERT proposes text embeddings in their context. Another model similar to multimodal representations and similarity-based sampling relationships is a Graph Neural Network. It is experimentally demonstrated that the proposed framework is characterized by a total classification accuracy of 0.7676 compared to baseline and conventional attention-based models. The additional outcomes of Precision show that enhanced retrieval performance was obtained, which highlights the fact that multimodal fusion that is strengthened by mental attention can be effective in the sentiment classification task.