Skip to main content
QUICK REVIEW

[论文解读] Call Attention to Rumors: Deep Attention Based Recurrent Neural Networks for Early Rumor Detection

Tong Chen, Lin Wu|arXiv (Cornell University)|Apr 20, 2017
Misinformation and Its Impacts参考文献 33被引用 20
一句话总结

本文提出 CallAtRumors,一种基于深度注意力机制的循环神经网络,通过在 LSTMs 中引入软注意力机制,从连续的社交媒体帖子中学习时间表征,实现早期谣言检测。该模型在高文本重复背景下仍能有效聚焦于关键且具有区分性的特征,相较于最先进方法表现更优,在微博数据集上 F-measure 达 0.8672,在样本数据集上达 0.9061,平均比人工事实核查提前 20.47 小时检测到谣言。

ABSTRACT

The proliferation of social media in communication and information dissemination has made it an ideal platform for spreading rumors. Automatically debunking rumors at their stage of diffusion is known as extit{early rumor detection}, which refers to dealing with sequential posts regarding disputed factual claims with certain variations and highly textual duplication over time. Thus, identifying trending rumors demands an efficient yet flexible model that is able to capture long-range dependencies among postings and produce distinct representations for the accurate early detection. However, it is a challenging task to apply conventional classification algorithms to rumor detection in earliness since they rely on hand-crafted features which require intensive manual efforts in the case of large amount of posts. This paper presents a deep attention model on the basis of recurrent neural networks (RNN) to learn extit{selectively} temporal hidden representations of sequential posts for identifying rumors. The proposed model delves soft-attention into the recurrence to simultaneously pool out distinct features with particular focus and produce hidden representations that capture contextual variations of relevant posts over time. Extensive experiments on real datasets collected from social media websites demonstrate that (1) the deep attention based RNN model outperforms state-of-the-arts that rely on hand-crafted features; (2) the introduction of soft attention mechanism can effectively distill relevant parts to rumors from original posts in advance; (3) the proposed method detects rumors more quickly and accurately than competitors.

研究动机与目标

  • 为应对社交媒体中早期谣言检测的挑战,因数据量大且重复度高,人工特征工程不可行。
  • 开发一种灵活的端到端深度学习模型,捕捉序列帖子中的长程时间依赖关系。
  • 通过选择性关注演化谣言讨论中最具相关性的词语和短语,提升检测准确率与提前度。
  • 减少对手工特征的依赖,同时在大规模、高重复性的社交媒体数据上保持稳健性能。

提出的方法

  • 模型使用双向LSTM将连续的社交媒体帖子编码为上下文隐藏表征。
  • 在LSTM输出上应用软注意力机制,根据与谣言检测的相关性动态分配不同时间步的注意力权重。
  • 通过前馈网络对LSTM隐藏状态计算注意力权重,使模型能够聚焦于显著短语并降低重复内容带来的噪声。
  • 将注意力表征进行池化处理,并输入最终分类层,以判断帖子序列是否为谣言。
  • 采用交叉熵损失并使用时间反向传播进行端到端训练。
  • 文本特征通过帖子的TF-IDF向量表示,保留语义内容的同时降低维度。

实验结果

研究问题

  • RQ1基于深度注意力机制的RNN模型是否能在检测早期性和准确性上超越依赖手工特征的传统方法?
  • RQ2软注意力机制在识别并强调重复社交媒体帖子中关键区分性短语方面的有效性如何?
  • RQ3在病毒式谣言讨论中常见的高文本重复背景下,该模型的性能保持程度如何?
  • RQ4与人工事实核查时间线及其他SOTA方法相比,该模型的检测提前度如何?

主要发现

  • 在微博数据集上,CallAtRumors实现精确率87.10%、召回率86.34%,F-measure达0.8672,优于最先进方法。
  • 在包含1,193条谣言和6,387条非谣言的样本数据集上,CallAtRumors的F-measure为0.9061,高于CERT的0.8801。
  • 模型在谣言出现后平均提前20.47小时检测到谣言,显著早于人工事实核查的平均时间(54–72小时)。
  • 在仅使用10%–20%训练数据时,CallAtRumors在Twitter和微博数据集上分别比ML-GRU在精确率上高出5%、召回率高出4%,展现出更优的早期检测能力。
  • 注意力可视化结果表明,模型能有效突出具有区分性的关键词(如“disqualified”、“Trump”),同时抑制冗余或重复的短语。
  • 注意力机制提升了模型对文本重复的鲁棒性,即使在事件中80%的帖子为重复内容时,仍能实现更优的特征提炼。

更好的研究,从现在开始

从阅读论文到最终审阅,大幅缩短您的研究时间。

无需绑定信用卡

本解读由 AI 生成,并经人工编辑审核。