Knowledge-Enhanced Hierarchical Information Correlation Learning for Multi-Modal Rumor Detection

TL;DR

This paper introduces KhiCL, a novel multi-modal rumor detection method that models hierarchical semantic correlations and incorporates external knowledge to improve detection accuracy on social media data.

Contribution

It proposes a knowledge-enhanced hierarchical correlation learning framework that jointly models basic and high-order semantic correlations across modalities using external knowledge graphs.

Findings

KhiCL outperforms existing methods on multiple datasets.

The approach effectively captures complex semantic correlations.

Knowledge integration improves rumor detection accuracy.

Abstract

The explosive growth of rumors with text and images on social media platforms has drawn great attention. Existing studies have made significant contributions to cross-modal information interaction and fusion, but they fail to fully explore hierarchical and complex semantic correlation across different modality content, severely limiting their performance on detecting multi-modal rumor. In this work, we propose a novel knowledge-enhanced hierarchical information correlation learning approach (KhiCL) for multi-modal rumor detection by jointly modeling the basic semantic correlation and high-order knowledge-enhanced entity correlation. Specifically, KhiCL exploits cross-modal joint dictionary to transfer the heterogeneous unimodality features into the common feature space and captures the basic cross-modal semantic consistency and inconsistency by a cross-modal fusion layer. Moreover, considering the description of multi-modal content is narrated around entities, KhiCL extracts visual and textual entities from images and text, and designs a knowledge relevance reasoning strategy to find the shortest semantic relevant path between each pair of entities in external knowledge graph, and absorbs all complementary contextual knowledge of other connected entities in this path for learning knowledge-enhanced entity representations. Furthermore, KhiCL utilizes a signed attention mechanism to model the knowledge-enhanced entity consistency and inconsistency of intra-modality and inter-modality entity pairs by measuring their corresponding semantic relevant distance. Extensive experiments have demonstrated the effectiveness of the proposed method.