发表机构
University of Konstanz; MPI for Dynamics and Self-Organization; University of Göttingen; Complexity Science Hub Vienna; Centro Ricerche Enrico Fermi（康斯坦茨大学; 动力学与自组织马克斯·普朗克研究所; 哥廷根大学; 维也纳复杂科学中心; 恩里科·费米研究中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对不可靠新闻检测难题，提出领域级方法构建领域共分享网络，利用图神经网络（如GraphSAGE）结合网络拓扑信息，显著提升了不可靠新闻领域检测的准确率，在无法进行内容分析时仍有效。
AI 中文摘要
基于内容的不可靠新闻检测难度日益增大，因为低可信度信源会模仿可信新闻，且生成式AI使得伪造内容更难被识别。本文探究网络结构能否提升新闻可信度分类，采用领域级方法将重点从单篇文章转向信源可信度。我们基于Telegram聊天中的URL分享模式构建了经统计验证的领域共分享网络，发现存在按可信度的同配混合现象：低可信度领域相互聚集，高可信度领域也相互聚集。利用该结构，我们对比了图神经网络（GNN）与不考虑网络的基线模型，使用了内容感知特征（多语言文本嵌入）和内容无关特征（传播动力学）两类特征。在相同特征下，GNN的表现始终优于多层感知机（MLP），其中GraphSAGE在两种设置下均表现最佳：使用内容特征时准确率为0.63，不使用内容特征时为0.53，相比不考虑网络的基线模型取得了13%-14%的相对提升。因此，网络拓扑结构可系统性地提升领域可信度评估，即使在无法进行内容分析时也能保持有效性。
英文摘要
Content-based detection of unreliable news is increasingly difficult, as low-reliability sources mimic credible journalism and generative AI makes fabricated content harder to flag. We ask whether network structure can improve news reliability classification, taking a domain-level approach that shifts the focus from individual articles to source reliability. From URL-sharing patterns in Telegram chats, we build a statistically validated domain co-sharing network and find assortative mixing by reliability: low-reliability domains group together, as do reliable ones. Exploiting this structure, we compare Graph Neural Networks against network-unaware baselines using both content-aware features (multilingual text embeddings) and content-agnostic features (spreading dynamics). GNNs consistently outperform Multi-Layer Perceptrons on identical features, with GraphSAGE best in both settings (accuracy 0.63 with content, 0.53 without), a 13-14% relative gain over the network-unaware baseline. Network topology thus systematically improves domain reliability assessment, and remains effective even when content analysis is infeasible.
