用Transformer文本表示增强GNN，提升社交平台假新闻检测效果
Enriching GNNs with Text Contextual Representations for Detecting Disinformation Campaigns on Social Media
- 将Transformer生成的上下文文本特征融入GNN，捕捉语义信息
- 相比无文本特征模型，宏平均F1提升33.8%；比静态文本表示高9.3%
- 适用于需要语义理解的社交网络虚假信息检测任务
社交媒体上的虚假信息带来社会与技术双重挑战，亟需稳健的检测系统。尽管先前研究已尝试将文本信息整合进传播网络，但尚未充分利用基于Transformer的语言模型所带来的高质量上下文文本表示。本文通过将基于Transformer的文本特征引入图神经网络（GNN），实现假新闻检测。实验表明，上下文文本表示能显著提升GNN性能：相较无文本特征模型，宏平均F1提升33.8%；相较静态文本表示，提升9.3%。我们还研究了不同特征来源的影响及噪声数据增强的效果。本方法为后续研究提供新方向，并已公开代码。
原文摘要 · Abstract (English)
Disinformation on social media poses both societal and technical challenges, requiring robust detection systems. While previous studies have integrated textual information into propagation networks, they have yet to fully leverage the advancements in Transformer-based language models for high-quality contextual text representations. This work addresses this gap by incorporating Transformer-based textual features into Graph Neural Networks (GNNs) for fake news detection. We demonstrate that contextual text representations enhance GNN performance, achieving 33.8% relative improvement in Macro F1 over models without textual features and 9.3% over static text representations. We further investigate the impact of different feature sources and the effects of noisy data augmentation. We expect our methodology to open avenues for further research, and we made code publicly available.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。