Multi-level Interaction Network for Multi-Modal Rumor Detection

The rapid development of social platforms has intensified the creation and spread of rumors. Hence, automatic Rumor Detection (RD) is an important and urgent task to maintain public interests and social harmony. As one of the frontier subtasks in RD, Multi-Modal Rumor Detection (MMRD) has become a new research hotspot currently. Previous methods focused on inferring clues from media content, ignoring the rich knowledge contained in texts and images. Moreover, existing methods are limited to cascade operators to encode multi-modal relationships, which cannot reflect the interactions between multiple modalities. In this paper, we propose a novel Multi-level Interaction Network (MIN), which regards entities and their relevant external knowledge as priori knowledge to provide additional features. Meanwhile, in MIN, we design a Co-Attention Network (CAN) to implement three-level interactions (i.e., the interaction between entities and image, text and external knowledge, refined text and refined image) for multi-modal fusion. Experimental results on the three public datasets (i.e., Fakeddit, Pheme and Weibo) demonstrate that our MIN model outperforms the state-of-the-arts.