[论文解读] Fake News Detection on Social Media using Geometric Deep Learning

Federico Monti, Fabrizio Frasca+3 more|arXiv (Cornell University)|Feb 10, 2019

Misinformation and Its Impacts参考文献 45被引用 188

一句话总结

本论文提出一种基于传播与图的假新闻检测器，采用 Twitter cascades 上的几何深度学习，在 ROC AUC 和早期检测性能方面表现出色。

ABSTRACT

Social media are nowadays one of the main news sources for millions of people around the globe due to their low cost, easy access and rapid dissemination. This however comes at the cost of dubious trustworthiness and significant risk of exposure to 'fake news', intentionally written to mislead the readers. Automatically detecting fake news poses challenges that defy existing content-based analysis approaches. One of the main reasons is that often the interpretation of the news requires the knowledge of political or social context or 'common sense', which current NLP algorithms are still missing. Recent studies have shown that fake and real news spread differently on social media, forming propagation patterns that could be harnessed for the automatic fake news detection. Propagation-based approaches have multiple advantages compared to their content-based counterparts, among which is language independence and better resilience to adversarial attacks. In this paper we show a novel automatic fake news detection model based on geometric deep learning. The underlying core algorithms are a generalization of classical CNNs to graphs, allowing the fusion of heterogeneous data such as content, user profile and activity, social graph, and news propagation. Our model was trained and tested on news stories, verified by professional fact-checking organizations, that were spread on Twitter. Our experiments indicate that social network structure and propagation are important features allowing highly accurate (92.7% ROC AUC) fake news detection. Second, we observe that fake news can be reliably detected at an early stage, after just a few hours of propagation. Third, we test the aging of our model on training and testing data separated in time. Our results point to the promise of propagation-based approaches for fake news detection as an alternative or complementary strategy to content-based approaches.

研究动机与目标

• 由于需要上下文和常识需求，挑战在于超越基于内容的方法的假新闻检测。
• 提出一个基于图的、传播感知的模型，将内容、用户和网络特征融合。
• 证明传播模式在大规模 Twitter 数据集上对假新闻检测提供了强信号。

提出的方法

• 提出一个四层图卷积神经网络，在每个卷积层使用图注意力的两次图卷积和两次全连接层。
• 整合异构数据：将用户画像、用户活动、社交网络结构和新闻传播作为单一图输入 Gu 对每个 URL/级联。
• 通过链接共享 URL 的推文并通过关注关系和扩散路径来计算输入图；边缘携带多关系特征，在卷积层中通过注意力更新。
• 使用铰链损失（无正则化）和 SELU 激活，采用 AMSGrad，学习率为 5e-4。
• 在 Twitter 数据上进行 URL 维和级联维的评估（2013–2018），级联超过 6 条推文且扩散时间窗为 24 小时。

实验结果

研究问题

• RQ1 传播和社交网络结构特征是否单独就能在 Twitter 上可靠检测假新闻（不依赖内容）？
• RQ2 按 URL 与按级联分类时性能有何差异，检测能在多早达到有效？
• RQ3 模型对培训与测试数据之间随时间的老化有多大鲁棒性？
• RQ4 最小级联规模对检测性能有何影响？
• RQ5 哪些特征组（用户画像、活动、网络/传播、内容）对预测贡献最大？

主要发现

• URL 维 ROC AUC 为 92.70%（±1.80）在五折上。
• 级联维 ROC AUC 为 88.30%（±2.74）在五折上。
• 扩散时间越长，准确性越高；URL 维在约 15 小时达到饱和，级联维在约 7 小时达到饱和。
• 消融实验显示用户画像和网络/传播特征对两种设定均为最重要。
• 模型老化：URL 维在约 180 天后性能下降，而级联维下降速度较慢（260 天后 ≤4%）。
• t-SNE 可视化揭示模型学到的可信与非可信用户之间的明显聚类。