CMA-R:用于解释谣言检测的因果中介分析
CMA-R:Causal Mediation Analysis for Explaining Rumour Detection
AI总结:
本文提出CMA-R方法,通过因果中介分析解释Twitter谣言检测模型的决策过程,识别显著推文及关键单词,与人类判断高度一致,提升黑盒系统的可解释性。
摘要:
我们应用因果中介分析来解释神经网络模型在Twitter谣言检测中的决策过程。在输入和网络层面进行的干预揭示了推文和单词对模型输出的因果影响。我们发现,我们的方法CMA-R——用于谣言检测的因果中介分析——能够识别出解释模型预测的显著推文,并在判定故事真实性的关键推文上与人类判断表现出高度一致。CMA-R还能进一步突出这些显著推文中具有因果影响力的单词,为这些黑盒谣言检测系统提供另一层可解释性和透明度。代码可在https://github.com/ltian678/cma-r获取。
英文摘要:
We apply causal mediation analysis to explain the decision-making process of neural models for rumour detection on Twitter. Interventions at the input and network level reveal the causal impacts of tweets and words in the model output. We find that our approach CMA-R -- Causal Mediation Analysis for Rumour detection -- identifies salient tweets that explain model predictions and show strong agreement with human judgements for critical tweets determining the truthfulness of stories. CMA-R can further highlight causally impactful words in the salient tweets, providing another layer of interpretability and transparency into these blackbox rumour detection systems. Code is available at: https://github.com/ltian678/cma-r.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。