MGM: Global Understanding of Audience Overlap Graphs for Predicting the Factuality and the Bias of News Media

TL;DR

This paper introduces MGM, a novel framework combining GNNs and PLMs within a variational EM approach to improve profiling of news media's bias and factuality by capturing long-range dependencies and structural information.

Contribution

The paper presents MediaGraphMind (MGM), a new method that enhances media profiling by integrating structural and textual features using a variational EM framework, outperforming existing models.

Findings

Achieved state-of-the-art results on media bias and factuality classification.

Effectively captures long-range dependencies in media graphs.

Improves both GNN and PLM performance through structural integration.

Abstract

In the current era of rapidly growing digital data, evaluating the political bias and factuality of news outlets has become more important for seeking reliable information online. In this work, we study the classification problem of profiling news media from the lens of political bias and factuality. Traditional profiling methods, such as Pre-trained Language Models (PLMs) and Graph Neural Networks (GNNs) have shown promising results, but they face notable challenges. PLMs focus solely on textual features, causing them to overlook the complex relationships between entities, while GNNs often struggle with media graphs containing disconnected components and insufficient labels. To address these limitations, we propose MediaGraphMind (MGM), an effective solution within a variational Expectation-Maximization (EM) framework. Instead of relying on limited neighboring nodes, MGM leverages features, structural patterns, and label information from globally similar nodes. Such a framework not only enables GNNs to capture long-range dependencies for learning expressive node representations but also enhances PLMs by integrating structural information and therefore improving the performance of both models. The extensive experiments demonstrate the effectiveness of the proposed framework and achieve new state-of-the-art results. Further, we share our repository1 which contains the dataset, code, and documentation