MViR: Multi-View Visual-Semantic Representation for Fake News Detection

TL;DR

This paper introduces MViR, a novel framework that captures multi-view visual-semantic features to improve fake news detection accuracy on social media datasets.

Contribution

It proposes a multi-view visual-semantic representation method using pyramid dilated convolution and feature fusion for enhanced fake news detection.

Findings

MViR outperforms existing methods on benchmark datasets.

The multi-view approach effectively captures diverse visual-semantic cues.

Experimental results demonstrate improved detection accuracy.

Abstract

With the rise of online social networks, detecting fake news accurately is essential for a healthy online environment. While existing methods have advanced multimodal fake news detection, they often neglect the multi-view visual-semantic aspects of news, such as different text perspectives of the same image. To address this, we propose a Multi-View Visual-Semantic Representation (MViR) framework. Our approach includes a Multi-View Representation module using pyramid dilated convolution to capture multi-view visual-semantic features, a Multi-View Feature Fusion module to integrate these features with text, and multiple aggregators to extract multi-view semantic cues for detection. Experiments on benchmark datasets demonstrate the superiority of MViR. The source code of FedCoop is available at https://github.com/FlowerinZDF/FakeNews-MVIR.