首页|以可解释工具重探基于深度学习的谣言检测

以可解释工具重探基于深度学习的谣言检测

扫码查看
[目的]探究基于内容的深度谣言检测模型能否真正识别谣言的关键语义.[方法]基于谣言检测任务的中英文基准数据集,本文分别利用基于局部代理模型的可解释工具LIME和基于合作博弈论的可解释工具SHAP,分析BERT模型所识别出的关键特征,并判断其是否能反映谣言特性.[结果]可解释工具在不同模型与数据集上计算得出的关键特征差异性较大,无法辨别模型识别的重要特征和谣言之间的语义关系.[局限]本文验证的数据集和模型数量都十分有限.[结论]基于深度学习的谣言检测模型仅拟合了训练集的特征,面向多样的真实场景缺少足够的泛化性和可解释性.
Revisiting Deep Learning-based Rumor Detection Models with Interpretable Tools
[Objective]This study explores whether content-based deep detection models can identify the semantics of rumors.[Methods]First,we use the BERT model to identify the key features of rumors from benchmark datasets in Chinese and English.Then,we utilized two interpretable tools,LIME,based on local surrogate models,and SHAP,based on cooperative game theory,to analyze whether these features can reflect the nature of rumors.[Results]The key features calculated by the interpretable tools on different models and datasets showed significant differences,and it is challenging to decide the semantic relationship between the features and rumors.[Limitations]The datasets and models examined in this study need to be expanded.[Conclusion]Deep learning-based rumor detection models only work with the features of the training set and lack sufficient generalization and interpretability for diverse real-world scenarios.

Rumor DetectionInterpretable Machine LearningDeep LearningLIMESHAP

贺国秀、任佳渝、李宗耀、林晨曦、蔚海燕

展开 >

华东师范大学经济与管理学院 上海 200062

谣言检测 可解释机器学习 深度学习 LIME SHAP

国家自然科学基金上海市哲学社会科学规划青年项目中央高校基本科研业务费专项Shanghai Philosophy and Social Science Planning Youth Project中央高校基本科研业务费专项

722040872022ETQ001722040872022ETQ001

2024

数据分析与知识发现
中国科学院文献情报中心

数据分析与知识发现

CSTPCDCSSCICHSSCD北大核心EI
影响因子:1.452
ISSN:2096-3467
年,卷(期):2024.8(4)
  • 36