Each Fake News is Fake in its Own Way: An Attribution Multi-Granularity Benchmark for Multimodal Fake News Detection

TL;DR

This paper introduces a new multi-granularity dataset and model for multimodal fake news detection, emphasizing the importance of understanding diverse fake news patterns beyond binary classification.

Contribution

It creates the first attributing multi-granularity dataset for fake news detection and proposes a novel model to leverage this data for improved detection and attribution.

Findings

mg dataset is challenging and reveals diverse fake news patterns.

The proposed model improves detection accuracy by utilizing multi-granularity clues.

Attribution setting offers new research directions for fake news analysis.

Abstract

Social platforms, while facilitating access to information, have also become saturated with a plethora of fake news, resulting in negative consequences. Automatic multimodal fake news detection is a worthwhile pursuit. Existing multimodal fake news datasets only provide binary labels of real or fake. However, real news is alike, while each fake news is fake in its own way. These datasets fail to reflect the mixed nature of various types of multimodal fake news. To bridge the gap, we construct an attributing multi-granularity multimodal fake news detection dataset \amg, revealing the inherent fake pattern. Furthermore, we propose a multi-granularity clue alignment model \our to achieve multimodal fake news detection and attribution. Experimental results demonstrate that \amg is a challenging dataset, and its attribution setting opens up new avenues for future research.