Rumor Classification through a Multimodal Fusion Framework and Ensemble Learning

TL;DR

This paper introduces MONITOR, a multimodal fusion framework utilizing advanced image features and ensemble learning models to improve rumor detection accuracy on social media by combining textual, visual, and metadata analysis.

Contribution

The paper proposes a novel multimodal fusion framework with advanced image features and demonstrates the effectiveness of ensemble learning models for rumor classification.

Findings

MONITOR outperforms existing machine learning baselines.

Ensemble models significantly enhance rumor detection performance.

Incorporating visual content improves classification accuracy.

Abstract

The proliferation of rumors on social media has become a major concern due to its ability to create a devastating impact. Manually assessing the veracity of social media messages is a very time-consuming task that can be much helped by machine learning. Most message veracity verification methods only exploit textual contents and metadata. Very few take both textual and visual contents, and more particularly images, into account. Moreover, prior works have used many classical machine learning models to detect rumors. However, although recent studies have proven the effectiveness of ensemble machine learning approaches, such models have seldom been applied. Thus, in this paper, we propose a set of advanced image features that are inspired from the field of image quality assessment, and introduce the Multimodal fusiON framework to assess message veracIty in social neTwORks (MONITOR), which exploits all message features by exploring various machine learning models. Moreover, we demonstrate the effectiveness of ensemble learning algorithms for rumor detection by using five metalearning models. Eventually, we conduct extensive experiments on two real-world datasets. Results show that MONITOR outperforms state-of-the-art machine learning baselines and that ensemble models significantly increase MONITOR's performance.