Graph Neural Networks for Misinformation Detection: Performance-Efficiency Trade-offs

TL;DR

This paper benchmarks various graph neural networks against traditional methods for misinformation detection, demonstrating that GNNs offer superior performance and efficiency across multiple datasets and languages.

Contribution

The study provides a comprehensive comparison of lightweight GNN architectures with non-graph models, highlighting their effectiveness and efficiency in misinformation detection tasks.

Findings

GNNs outperform non-graph baselines in F1 score across datasets.

GraphSAGE achieves up to 96.8% F1 on Kaggle.

GNNs maintain efficiency with comparable or lower inference times.

Abstract

The rapid spread of online misinformation has led to increasingly complex detection models, including large language models and hybrid architectures. However, their computational cost and deployment limitations raise concerns about practical applicability. In this work, we benchmark graph neural networks (GNNs) against non-graph-based machine learning methods under controlled and comparable conditions. We evaluate lightweight GNN architectures (GCN, GraphSAGE, GAT, ChebNet) against Logistic Regression, Support Vector Machines, and Multilayer Perceptrons across seven public datasets in English, Indonesian, and Polish. All models use identical TF-IDF features to isolate the impact of relational structure. Performance is measured using F1 score, with inference time reported to assess efficiency. GNNs consistently outperform non-graph baselines across all datasets. For example, GraphSAGE achieves 96.8% F1 on Kaggle and 91.9% on WELFake, compared to 73.2% and 66.8% for MLP, respectively. On COVID-19, GraphSAGE reaches 90.5% F1 vs. 74.9%, while ChebNet attains 79.1% vs. 66.4% on FakeNewsNet. These gains are achieved with comparable or lower inference times. Overall, the results show that classic GNNs remain effective and efficient, challenging the need for increasingly complex architectures in misinformation detection.