Interpretable Multimodal Misinformation Detection with Logic Reasoning

TL;DR

This paper introduces a neural-symbolic model for multimodal misinformation detection that combines interpretability with high performance, using logic reasoning and neural parameterization to enhance explainability and generalizability across datasets.

Contribution

The paper presents a novel logic-based neural model that integrates symbolic reasoning with neural learning for interpretable multimodal misinformation detection.

Findings

Effective on three public datasets (Twitter, Weibo, Sarcasm)

Achieves high performance with interpretability

Introduces five meta-predicates for generalization

Abstract

Multimodal misinformation on online social platforms is becoming a critical concern due to increasing credibility and easier dissemination brought by multimedia content, compared to traditional text-only information. While existing multimodal detection approaches have achieved high performance, the lack of interpretability hinders these systems' reliability and practical deployment. Inspired by NeuralSymbolic AI which combines the learning ability of neural networks with the explainability of symbolic learning, we propose a novel logic-based neural model for multimodal misinformation detection which integrates interpretable logic clauses to express the reasoning process of the target task. To make learning effective, we parameterize symbolic logical elements using neural representations, which facilitate the automatic generation and evaluation of meaningful logic clauses. Additionally, to make our framework generalizable across diverse misinformation sources, we introduce five meta-predicates that can be instantiated with different correlations. Results on three public datasets (Twitter, Weibo, and Sarcasm) demonstrate the feasibility and versatility of our model.