[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.
(Li Zongjian, Cheng Zhuru. Challenges and Countermeasures of Public Opinion Guidance in the New Media Time[J]. The Journal of Shanghai Administration Institute, 2016, 17(5): 76-85.)
(Li Luqi, Hou Li, Deng Shengli. Research on Influencing Factors of Network Misinformation Transmission Behaviors in Public Health Emergencies: A Case Study of Weibo Misinformation During the COVID-19[J]. Library and Information Service, 2022, 66(9): 4-13.)
doi: 10.13266/j.issn.0252-3116.2022.09.001
(Huang Xuejian, Ma Tinghuai, Wang Gensheng. Detecting Weibo Rumors Based on Hierarchical Semantic Feature Learning Model[J]. Data Analysis and Knowledge Discovery, 2023, 7(5): 81-91.)
[4]
Castillo C, Mendoza M, Poblete B. Predicting Information Credibility in Time-Sensitive Social Media[J]. Internet Research, 2013, 23(5): 560-588.
[5]
Shu K, Zhou X Y, Wang S H, et al. The Role of User Profiles for Fake News Detection[C]// Proceedings of the 2019 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining. New York: ACM, 2019: 436-439.
(Zu Kunlin, Zhao Mingwei, Guo Kai, et al. Research on the Detection of Rumor on Sina Weibo[J]. Journal of Chinese Information Processing, 2017, 31(3): 198-204.)
[7]
Ma J, Gao W, Wong K F. Detect Rumors in Microblog Posts Using Propagation Structure via Kernel Learning[C]// Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics. Stroudsburg: Association for Computational Linguistics, 2017: 708-717.
[8]
Shen S S, Lee H Y. Neural Attention Models for Sequence Classification: Analysis and Application to Key Term Extraction and Dialogue Act Detection[C]// Proceedings of the 17th Annual Conference of the International Speech Communication Association. San Francisco: ISCA, 2016: 2716-2720.
[9]
Bian T, Xiao X, Xu T Y, et al. Rumor Detection on Social Media with Bi-Directional Graph Convolutional Networks[C]// Proceedings of the AAAI Conference on Artificial Intelligence. Menlo Park: AAAI, 2020: 549-556.
[10]
Anggrainingsih R, Hassan G M, Datta A. BERT Based Classification System for Detecting Rumours on Twitter[OL]. arXiv Preprint, arXiv:2109.02975.
[11]
Zhong W J, Xu J J, Tang D Y, et al. Reasoning over Semantic-Level Graph for Fact Checking[OL]. arXiv Preprint, arXiv:1909.03745.
[12]
Kim B, Doshi-Velez F. Interpretable Machine Learning: The Fuss, the Concrete and the Questions[C]// Proceedings of the 32nd International Conference on Machine Learning. New York: ACM, 2017: 1-13.
[13]
Miller T. Explanation in Artificial Intelligence: Insights from the Social Sciences[J]. Artificial Intelligence, 2019, 267: 1-38.
doi: 10.1016/j.artint.2018.07.007
[14]
Ribeiro M T, Singh S, Guestrin C. ” Explaining the Predictions of Any Classifier[C]// Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2016: 1135-1144.
[15]
Ribeiro M T, Singh S, Guestrin C. Anchors: High-Precision Model-Agnostic Explanations[C]// Proceedings of the 32nd AAAI Conference on Artificial Intelligence. Menlo Park: AAAI, 2018: 1527-1535.
[16]
Selvaraju R R, Cogswell M, Das A, et al. Grad-Cam: Visual Explanations from Deep Networks via Gradient-based Localization[C]// Proceedings of the 16th IEEE International Conference on Computer Vision. Piscataway: IEEE, 2017: 618-626.
[17]
Bau D, Zhou B L, Khosla A, et al. Network Dissection: Quantifying Interpretability of Deep Visual Representations[C]// Proceedings of the 30th IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 3319-3327.
[18]
Montavon G, Lapuschkin S, Binder A, et al. Explaining Nonlinear Classification Decisions with Deep Taylor Decomposition[J]. Pattern Recognition, 2017, 65: 211-222.
[19]
Lundberg S M, Lee S I. A Unified Approach to Interpreting Model Predictions[C]// Proceedings of the 31st International Conference on Neural Information Processing Systems. New York: ACM, 2017: 4768-4777.
[20]
Shrikumar A, Greenside P, Kundaje A. Learning Important Features through Propagating Activation Differences[C]// Proceedings of the 34th International Conference on Machine Learning. New York: ACM, 2017: 3145-3153.
(Liu Tianchang, Wang Lei, Zhu Qinghua. Predicting User Churn of Smart Home-Based Care Services Based on SHAP Interpretation[J]. Data Analysis and Knowledge Discovery, 2024, 8(1): 40-54.)
(Yi Ming, Yao Yujia, Hu Min. An Interpretable Model for New Government Media Public Value Consensus Integrating XGBoost and SHAP: Taking the Top 10 Municipal Government Accounts of the Jinri Toutiao as an Example[J]. Library and Information Service, 2022, 66(16): 36-47.)
doi: 10.13266/j.issn.0252-3116.2022.16.004
(Zeng Ziming, Zhang Yu, Li Tingting. Detection of Potential Rumor Spreaders in Public Health Emergencies Based on Multi-Feature Fusion[J]. Library and Information Service, 2022, 66(13): 80-90.)
doi: 10.13266/j.issn.0252-3116.2022.13.008
[24]
Ayoub J, Yang X J, Zhou F. Combat COVID-19 Infodemic Using Explainable Natural Language Processing Models[J]. Information Processing & Management, 2021, 58(4): 102569.
[25]
Mikolov T, Chen K, Corrado G, et al. Efficient Estimation of Word Representations in Vector Space[OL]. arXiv Preprint, arXiv: 1301.3781.
(Li Hui, Chai Yaqing. Analyzing Sentiment Polarity of Comments Based on Attributes[J]. Data Analysis and Knowledge Discovery, 2017, 1(10): 1-11.)
[27]
Devlin J, Chang M W, Lee K, et al. BERT: Pre-Training of Deep Bidirectional Transformers for Language Understanding[C]// Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies. Stroudsburg: Association for Computational Linguistics, 2019: 4171-4186.
[28]
Rumelhart D E, Hinton G E, Williams R J. Learning Representations by Back-Propagating Errors[J]. Nature, 1986, 323(6088): 533-536.
(Jianlin Su. WoBERT: Word-based Chinese BERT model[EB/OL]. [2020-9-18] https://kexue.fm/archives/7758)
[30]
Chen Y H. Convolutional Neural Network for Sentence Classification[D]. Waterloo: University of Waterloo, 2015.
[31]
Johnson R, Zhang T. Deep Pyramid Convolutional Neural Networks for Text Categorization[C]// Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics. Stroudsburg: Association for Computational Linguistics, 2017: 562-570.
[32]
Schuster M, Paliwal K K. Bidirectional Recurrent Neural Networks[J]. IEEE Transactions on Signal Processing, 1997, 45(11): 2673-2681.
[33]
Vosoughi S, Roy D, Aral S. The Spread of True and False News Online[J]. Science, 2018, 359: 1146-1151.
doi: 10.1126/science.aap9559
pmid: 29590045
[34]
Solovev K, Pröllochs N. Moral Emotions Shape the Virality of COVID-19 Misinformation on Social Media[C]// Proceedings of the ACM Web Conference 2022. New York: ACM, 2022: 3706-3717.
[35]
Liu X M, Nourbakhsh A, Li Q Z, et al. Real-Time Rumor Debunking on Twitter[C]// Proceedings of the 24th ACM International on Conference on Information and Knowledge Management. New York: ACM, 2015: 1867-1870.
[36]
Ma J, Gao W, Wei Z Y, et al. Detect Rumors Using Time Series of Social Context Information on Microblogging Websites[C]// Proceedings of the 24th ACM International on Conference on Information and Knowledge Management. New York: ACM, 2015: 1751-1754.