MUSER: A MUlti-Step Evidence Retrieval Enhancement Framework for Fake News Detection
MUSER: A MUlti-Step Evidence Retrieval Enhancement Framework for Fake News Detection
复制标题
DOI：
10.1145/3580305.3599873
复制
发表时间：
2023-06
期刊：
影响因子：
--
通讯作者：
Hao Liao;Jiaohao Peng;Zhanyi Huang;Wei Zhang;Guang‐hua Li;Kai Shu;Xingyu Xie
中科院分区：
文献类型：
--
作者：
Hao Liao;Jiaohao Peng;Zhanyi Huang;Wei Zhang;Guang‐hua Li;Kai Shu;Xingyu Xie
网络虚假信息传播的便捷性，使得不怀好意的人可以操纵舆论，破坏社会稳定。最近，基于证据检索的假新闻检测越来越受欢迎，以可靠地识别假新闻并减少其影响。基于证据检索的方法可以通过计算证据与新闻中的主张之间的文本一致性来提高假新闻检测的可靠性。在本文中，我们提出了一种基于多步证据检索增强（MUSER）的假新闻检测框架，该框架模拟人类在阅读新闻、总结、查阅材料以及推断新闻真假的过程中的步骤。我们的模型可以显式地对多个证据之间的依赖关系进行建模，并通过多步检索对新闻验证所需的证据进行多步关联。此外，我们的模型能够通过段落检索和关键证据选择来自动收集现有证据，这可以省去手动证据收集的繁琐过程。我们对不同语言的真实世界数据集进行了广泛的实验，结果表明，我们提出的模型在 F1-Macro 中的假新闻检测性能优于最先进的基线方法，在 F1-Macro 中至少高出 3%，在 F1-Micro 中高出 4%。此外，它还为最终用户提供可解释的证据。
The ease of spreading false information online enables individuals with malicious intent to manipulate public opinion and destabilize social stability. Recently, fake news detection based on evidence retrieval has gained popularity in an effort to identify fake news reliably and reduce its impact. Evidence retrieval-based methods can improve the reliability of fake news detection by computing the textual consistency between the evidence and the claim in the news. In this paper, we propose a framework for fake news detection based on MUlti- Step Evidence Retrieval enhancement (MUSER), which simulates the steps of human beings in the process of reading news, summarizing, consulting materials, and inferring whether the news is true or fake. Our model can explicitly model dependencies among multiple pieces of evidence, and perform multi-step associations for the evidence required for news verification through multi-step retrieval. In addition, our model is able to automatically collect existing evidence through paragraph retrieval and key evidence selection, which can save the tedious process of manual evidence collection. We conducted extensive experiments on real-world datasets in different languages, and the results demonstrate that our proposed model outperforms state-of-the-art baseline methods for detecting fake news by at least 3% in F1-Macro and 4% in F1-Micro. Furthermore, it provides interpretable evidence for end users.