This is official code from the paper: Multimodal Fusion with BERT and Attention Mechanism for Fake News Detection
We proposed a scale-dot product attention mechanism to capture the relationship between text features and visual features. Experimental results showed that our approach performs better than the current state-of-the-art method (SpotFake model) on a public Twitter dataset by 3.1% accuracy.
Link to paper: https://arxiv.org/abs/2104.11476