基于User-BERT模型的微博谣言检测
Microblog Rumor Detection Based on User-BERT
DOI: 10.12677/CSA.2021.114088, PDF,   
作者: 缪 鑫：广东工业大学，广东 广州
关键词: 谣言检测；BERT；深度学习；自然语言处理；Rumor Detection； BERT； Deep Learning； NLP
摘要: 随社交媒体的快速发展，微博已经成为人们获取信息的主要平台。它给人们生活带来便利的同时，也带来了谣言泛滥的问题。有越来越多研究投入到谣言检测中，从早期的特征工程方法到近期的深度学习方法。但是，目前的工作没有充分利用预训练语言模型与其它特征相结合。因此，文本推出User-BERT模型，使BERT模型能够充分利用文本和用户特征。它使用BERT模型对原文和评论文本进行编码，得到文本表示向量再与用户属性向量结合，最后由深度分类器对其进行解析并预测。在公开微博数据集上，User-BERT取得了当前最好的结果。
Abstract: With the rapid development of social media, Sina weibo has become the main platform for people to obtain information. While it brings convenience to people’s lives, it also brings the problem of spreading rumors. More and more research is devoted to rumor detection, from early feature engineering methods to recent deep learning methods. However, the current work does not make full use of the pretrained language model combined with other features. Therefore, this work introduces the User-BERT model, which enables the BERT model to make full use of text and user characteristics. It uses the BERT model to encode text of source post and comments, obtains the text representation vector and combines it with the user attribute vector, and it finally is parsed by the deep classifier. On the public weibo dataset, User-BERT has achieved the best results currently.
文章引用：缪鑫. 基于User-BERT模型的微博谣言检测[J]. 计算机科学与应用, 2021, 11(4): 859-866. https://doi.org/10.12677/CSA.2021.114088

参考文献

[1] 尹鹏博, 彭成, 潘伟民. 基于集成学习的微博谣言早期检测[J]. 微电子学与计算机, 2021, 38(1): 83-88.
[2] Liu, X., Nour-bakhsh, A., Li, Q., et al. (2015) Real-Time Rumor Debunking on Twitter. Proceedings of the 24th ACM International on Conference on Information and Knowledge Management, Melbourne, 19-23 October 2015, 1867- 1870. [Google Scholar] [CrossRef] 
[3] Ma, J., Gao, W., Wei, Z., et al. (2015) Detect Rumors Using Time Series of Social Context Information on Microblogging Websites. Proceedings of the 24th ACM International on Conference on Information and Knowledge Management, Melbourne, 19-23 October 2015, 1751-1754. [Google Scholar] [CrossRef] 
[4] Ma, J., Gao, W., Mitra, P., et al. (2016) Detecting Rumors from Microblogs with Recurrent Neural Networks.
[5] Wang, Z. and Guo, Y. (2020) Rumor Events Detection Enhanced by Encoding Sentimental Information into Time Series Division and Word Representations. Neurocomputing, 397, 224-243. [Google Scholar] [CrossRef] 
[6] Yu, F., Liu, Q., Wu, S., et al. (2017) A Convolutional Approach for Misin-formation Identification. Proceedings of the 26th International Joint Conference on Artificial Intelligence, Melbourne, 19-25 August 2017, 3901-3907. [Google Scholar] [CrossRef] 
[7] Bian, T., Xiao, X., Xu, T., et al. (2020) Rumor Detection on Social Media with Bi-Directional Graph Convolutional Networks. Proceedings of the AAAI Conference on Artificial Intelligence, 34, 549-556. [Google Scholar] [CrossRef] 
[8] Geng, Y., Lin, Z., Fu, P., et al. (2019) Rumor Detection on Social Media: A Mul-ti-View Model Using Self-Attention Mechanism. In: International Conference on Computational Science, Springer, Cham, 339-352. [Google Scholar] [CrossRef] 
[9] Devlin, J., Chang, M.W., Lee, K., et al. (2018) Bert: Pre-Training of Deep Bidirectional Transformers for Language Understanding.
[10] Vaswani, A., Shazeer, N., Parmar, N., et al. (2017) Attention Is All You Need.
[11] Li, Q., Zhang, Q. and Si, L. (2019) Rumor Detection by Exploiting User Credibility Information, Attention and Multi-Task Learning. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, 28 July-2 August 2019, 1173-1179. [Google Scholar] [CrossRef] 
[12] Kipf, T.N. and Welling, M. (2016) Semi-Supervised Classification with Graph Convolutional Networks.
[13] Liu, W., Wen, Y., Yu, Z., et al. (2016) Large-Margin Softmax Loss for Convolutional Neural Networks. The 33rd International Conference on Machine Learning (ICML 2016), New York, 19-24 June 2016, 7.
[14] Lu, Y.J. and Li, C.T. (2020) GCAN: Graph-Aware Co-Attention Networks for Explainable Fake News Detection on Social Media. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, July 2020, 505-514. [Google Scholar] [CrossRef] 
[15] Li, Q., Zhang, Q., Si, L., et al. (2019) Rumor Detection on Social Media: Da-tasets, Methods and Opportunities. Proceedings of the Second Workshop on Natural Language Processing for Internet Freedom: Censorship, Disinformation, and Propaganda, Hong Kong, November 2019, 66-75. [Google Scholar] [CrossRef]