A mutual attention based multimodal fusion for fake news detection on social network

As the advance of social networks, the emergency of fake news has been the major threat for information security, privacy, and trustworthiness. The fake news can leverage multimedia contents to fabricate evidences or mislead readers, which damages a lot in machine learning and network systems. In this work, we explored the task of multimodal fake news detection. The major challenge of fake news detection stems from the modality fusion by abundant information. Overcoming the limitations of the current models, we tackle the challenge of learning corrections between modalities in news, and substantially proposed a mutual attention neural network (MANN) that can learn the relationship between each different modality. Our model consists of four components: multimodal feature extractor, mutual attention fusion, fake news detector and irrelevant event discriminator. The performance of our proposed architecture is evaluated on Weibo dataset, which indicates the MANN model outperforms the state-of-the-arts.