Skip to main content
QUICK REVIEW

[论文解读] Combat COVID-19 Infodemic Using Explainable Natural Language Processing Models

Jackie Ayoub, X. Jessie Yang|arXiv (Cornell University)|Feb 28, 2021
Misinformation and Its Impacts参考文献 29被引用 8
一句话总结

本文提出了一种基于DistilBERT和SHAP的可解释NLP模型,用于高精度检测COVID-19虚假信息,并提升了公众信任度。该模型在精心筛选的数据集上达到97.2%的准确率,在共享任务数据集上达到93.8%的准确率,而SHAP解释显著提高了实验条件下的用户信任度和信息分享意愿。

ABSTRACT

Misinformation of COVID-19 is prevalent on social media as the pandemic unfolds, and the associated risks are extremely high. Thus, it is critical to detect and combat such misinformation. Recently, deep learning models using natural language processing techniques, such as BERT (Bidirectional Encoder Representations from Transformers), have achieved great successes in detecting misinformation. In this paper, we proposed an explainable natural language processing model based on DistilBERT and SHAP (Shapley Additive exPlanations) to combat misinformation about COVID-19 due to their efficiency and effectiveness. First, we collected a dataset of 984 claims about COVID-19 with fact checking. By augmenting the data using back-translation, we doubled the sample size of the dataset and the DistilBERT model was able to obtain good performance (accuracy: 0.972; areas under the curve: 0.993) in detecting misinformation about COVID-19. Our model was also tested on a larger dataset for AAAI2021 - COVID-19 Fake News Detection Shared Task and obtained good performance (accuracy: 0.938; areas under the curve: 0.985). The performance on both datasets was better than traditional machine learning models. Second, in order to boost public trust in model prediction, we employed SHAP to improve model explainability, which was further evaluated using a between-subjects experiment with three conditions, i.e., text (T), text+SHAP explanation (TSE), and text+SHAP explanation+source and evidence (TSESE). The participants were significantly more likely to trust and share information related to COVID-19 in the TSE and TSESE conditions than in the T condition. Our results provided good implications in detecting misinformation about COVID-19 and improving public trust.

研究动机与目标

  • 为应对社交媒体上日益严重的COVID-19虚假信息威胁,开发一种高精度且可信的检测模型。
  • 通过SHAP引入可解释性,提升公众对自动化虚假信息检测的信任度。
  • 评估不同形式的模型解释(仅文本、文本+SHAP、文本+SHAP+证据)对用户信任度和信息分享行为的影响。
  • 通过回译技术进行数据增强,在仅984条经过核实的声明的有限数据集上提升模型性能。

提出的方法

  • 在包含984条关于COVID-19的经核实声明的数据集上微调DistilBERT,以高精度分类虚假信息。
  • 采用回译技术进行数据增强,将数据集规模扩大一倍,以提升模型泛化能力。
  • 使用SHAP(Shapley加法解释)生成局部可解释性,通过将预测决策归因于单个输入标记来实现。
  • 开展一项被试间实验,设置三种条件:仅文本(T)、文本+SHAP(TSE)以及文本+SHAP+来源与证据(TSESE),以评估信任度与分享行为。
  • 使用统计分析比较不同实验条件下用户信任度与分享意愿的差异。
  • 在AAAI2021 COVID-19虚假新闻检测共享任务数据集上验证模型性能,以确保其鲁棒性。

实验结果

研究问题

  • RQ1在基于DistilBERT的虚假信息检测模型中集成SHAP解释是否能显著提升用户对模型预测的信任度?
  • RQ2在SHAP解释之外增加来源与证据信息,是否会影响用户分享虚假信息相关内容的意愿?
  • RQ3通过回译进行数据增强是否能提升DistilBERT模型在检测COVID-19虚假信息方面的性能?
  • RQ4所提出的可解释模型是否在小规模与大规模数据集上均优于传统机器学习模型?
  • RQ5不同解释粒度水平下,参与者信任度与分享意图的差异程度如何?

主要发现

  • 在数据增强后,模型在原始984条声明数据集上达到97.2%的准确率和0.993的AUC,表现出优异的检测性能。
  • 在更大的AAAI2021共享任务数据集上,模型达到93.8%的准确率和0.985的AUC,优于传统机器学习模型。
  • 在TSE(文本+SHAP)和TSESE(文本+SHAP+来源与证据)条件下的参与者,显著更倾向于信任并分享信息,相较于T(仅文本)条件。
  • TSE与TSESE条件之间未发现显著差异,表明在此情境下,来源与证据可能无法在SHAP解释的基础上进一步增强信任度。
  • 研究证实,可解释人工智能模型可显著提升公众对自动化虚假信息检测系统的信任度。
  • 部分参与者表示SHAP解释在某些情况下难以理解,表明未来工作需设计更直观的解释界面。

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。