MUSER : A MUlti-Step Evidence Retrieval Enhancement Framework for Fake News Detection 

 SIGKDD Conference on Knowledge Discovery and Data Mining - Applied Data Science Track

Hao Liao¹   Jiaohao Peng¹   Zhanyi Huang¹   WeiZhang¹   Guanghua Li¹  Kai Shu²   Xing Xie³

¹Shenzhen University   ²Illinois Institute of Technology   ³Microsoft Research Asia

Abstract

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 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 evidences, 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.

Figure 1: Overview of our framework.

Figure 2: Results of retrieve step comparison study.

Figure 3: Results of ablation study.

Figure 4: A verification example generated by MUSER in the Case study.

Acknowledgement

Thanks to the anonymous reviewers for their valuable comments and constructive feedback. The authors acknowledge financial support from the National Natural Science Foundation of China (Grant Nos. 62276171 and 62072311), Shenzhen Fundamental Research-General Project (Grant Nos. JCYJ20190808162601658, 20220811155803001 and 20210324094402008)，CCF-Baidu Open Fund (Grant No. OF2022028), and Swiftlet Fund Fintech funding. Kai Shu acknowledges financial support from NSF (Grant No. SaTC-2241068).

Bibtex

@inproceedings{

liao2023muser,

title={{MUSER} : A {MU}lti-Step Evidence Retrieval Enhancement Framework for Fake News Detection},

author={Hao Liao and JiaHao Peng and Zhanyi Huang and Wei Zhang and Guanghua Li and Kai Shu and Xing Xie},

booktitle={29th SIGKDD Conference on Knowledge Discovery and Data Mining - Applied Data Science Track},

year={2023},

url={https://openreview.net/forum?id=UPu1ETlmrS}

}

Downloads