基于局部和全局特征聚合的虚假新闻检测方法

doi:10.3778/j.issn.1002-8331.2312-0108

摘要/Abstract

摘要： 在虚假新闻检测的问题上，现有的方法大多通过捕捉上下文语义特征、对照外部知识库来判断新闻的真实性，但很多研究人员忽略了新闻在发布时期各大社交媒体的新闻生态。针对上述问题，提出一种基于局部和全局特征聚合的虚假新闻检测方法。具体来说，设计了全局环境感知模块和局部环境感知模块，其中全局环境感知模块通过均值池化、全连接、注意力机制等操作获得全局特征，局部环境感知模块通过将文本向量进行聚类、均值池化、哈达玛乘积、多层感知器、注意力机制等操作获得局部特征。利用融合机制将这些特征进行聚合，与其他虚假新闻检测器协同工作，用以验证新闻的真实性。在微博和推特两个新闻文本数据集上进行了对比实验，实验结果表明提出的方法可以有效提取全局和局部环境中的新闻文本特征，从而提高检测精度。

关键词: 虚假新闻检测, 注意力机制, 特征提取, 社交媒体

Abstract: On the issue of fake news detection, existing works rely on capturing contextual semantic features and referencing external knowledge bases to judge the authenticity of news, while neglecting the public opinion orientation at the time of news publication. To fill the gap, a fake news detection method based on local and global feature aggregation is proposed. In a more specific context, both a global environment perception module and a local environment perception module have been designed. The global environment perception module utilizes operations such as average pooling, fully connected layers, and attention mechanisms to extract global features, The local environment perception module obtains local features by performing operations such as clustering, average pooling, hadamard product, multi-layer perceptron, and attention mechanism on text vectors. Subsequently, these features are consolidated using a fusion mechanism and, in the end, work in conjunction with other fake news detectors to authenticate the news. Comparative experiments are conducted on news text datasets from both Weibo and Twitter. The experimental results demonstrate that the proposed method is effective in extracting news text features from both global and local environments, consequently enhancing detection accuracy.

Key words: fake news detection, attention mechanism, feature extraction, social media

杨书新, 丁祺伟. 基于局部和全局特征聚合的虚假新闻检测方法[J]. 计算机工程与应用, 2025, 61(9): 139-147.

YANG Shuxin, DING Qiwei. Fake News Detection Method Based on Local and Global Feature Aggregation[J]. Computer Engineering and Applications, 2025, 61(9): 139-147.

参考文献

[1] 毛震东,赵博文,白嘉萌,等. 基于传播意图特征的虚假新闻检测方法综述[J]. 信号处理, 2022, 38(6):1155-1169.
MAO Z D, ZHAO B W, BAI J M, et al. Review of fake news detection methods based on the features of propagation intention[J]. Journal of Signal Processing, 2022, 38(6):1155-1169.
[2] MA J, GAO W, MITRA P, et al. Detecting rumors from microblogs with recurrent neural networks[C]//Proceedings of the 25th International Joint Conference on Artificial Intelligence, 2016:3818-3824.
[3] 毕蓓,潘慧瑶,陈峰,等. 基于异构图注意力网络的微博谣言监测模型[J]. 计算机应用, 2021, 41(12):3546-3550.
BI B, PAN H, CHEN F, et al. Microblog rumor detection model based on heterogeneous graph attention network[J]. Journal of Computer Applications, 2021, 41(12):3546-3550.
[4] 高玉君,梁刚,蒋方婷,等. 社会网络谣言检测综述[J]. 电子学报, 2020, 48(7):1421-1435.
GAO Y J, LIANG G, JIANG F T, et al. Social network rumor detection: a survey[J]. Acta Electronica Sinica, 2020, 48(7):1421-1435.
[5] KUMAR A, SANGWAN S R. Rumor detection using machine learning techniques on social media[C]//Proceedings of the Conference on Innovative Computing and Communications, 2019: 213-221.
[6] KUMAR S, CARLEY K M. Tree LSTMs with convolution units to predict stance and rumor veracity in social media conversations[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2019: 5047-5058.
[7] CASTILLO C, MENDOZA M, POBLETE B. Information credibility on twitter[C]//Proceedings of the 20th International Conference on World Wide Web, 2011: 675-684.
[8] YANG F, LIU Y, YU X, et al. Automatic detection of rumor on sina weibo[C]//Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data, 2012: 1-7.
[9] KWON S, CHA M, JUNG K, et al. Prominent features of rumor propagation in online social media[C]//Proceedings of the 13th International Conference on Data Mining, 2013: 1103-1108.
[10] CHEN T, YIN H, CHEN H, et al. Air: attentional intention-aware recommender systems[C]//Proceedings of the 35th International Conference on Data Engineering, 2019: 304-315.
[11] YU F, LIU Q, WU S, et al. A convolutional approach for misinformation identification[C]//Proceedings of the 26th International Joint Conference on Artificial Intelligence, 2017:3901-3907.
[12] 范昊,何灏. 融合上下文特征和BERT词嵌入的新闻标题分类研究[J]. 情报科学, 2022, 40(6): 90-97.
FAN H, HE H. News title classification based on contextual features and bert word embedding[J]. Information Science, 2022, 40(6): 90-97.
[13] HU Y, PAN Q, HOU W, et al. Rumor spreading model with the different attitudes towards rumors[J]. Physica A: Statistical Mechanics and its Applications, 2018, 502: 331-344.
[14] SHIRALKAR P, FLAMMINI A, MENCZER F, et al. Finding streams in knowledge graphs to support fact checking[C]//Proceedings of the IEEE International Conference on Data Mining, 2017: 859-864.
[15] PAN J Z, PAVLOVA S, LI C, et al. Content based fake news detection using knowledge graphs[C]//Proceedings of the 17th International Semantic Web Conference, 2018: 669-683.
[16] CUI L, SEO H, TABAR M, et al. DETERRENT: knowledge guided grapy attention network for detecting healthcare misinformation[C]//Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2020: 492-502.
[17] 郭秋实,李晨曦,刘金硕,等. 引入知识表示的图卷积网络谣言检测方法[J]. 计算机应用研究, 2022, 39(7): 2032-2036.
GUO Q S, LI C X, LIU J S, et, al. Rumor detection with knowledge representation and graph convolutional network [J]. Application Research of Computers, 2022, 39(7): 2032-2036.
[18] 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, 2019: 4171-4186.
[19] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing, 2017: 6000-6100.
[20] VOSOUGHI S, ROY D, ARAL S. The spread of true and false news online[J]. Science, 2018, 359(6380): 1146-1151.
[21] SONG C, YANG C, CHEN H, et al. CED: credible early detection of social media rumors[J]. IEEE Transactions on Knowledge and Data Engineering, 2019, 33(8): 3035-3047.
[22] SHENG Q, CAO J, ZHANG X, et al. Article reranking by memory-enhanced key sentence matching for detecting previously fact-checked claims[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Proceedings, 2021: 5468-5481.
[23] KOCHKINA E, LIAKATA M, ZUBIAGA A. All-in-one: multi-task learning for rumor verification[C]//Proceedings of the 27th International Conference on Computational Linguistics, 2018: 3402-3413.
[24] AUGENSTEIN I, LIOMA C, WANG D, et al. MultiFC: a real-world multi-domain dataset for evidence-based fact checking of claims[C]//Proceedings of the 9th International Joint Conference on Natural Language Processing, 2019: 4685-4697.
[25] SHENG Q, CAO J, ZHANG X, et al. Zoom out and observe: news environment perception for fake news detection[C]//Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, 2022: 4543-4556.
[26] GRAVES A, SCHMIDHUBER J. Framewise phoneme classification with bidirectional lstm and other neural network architectures[J]. Neural Network, 2005, 18(5/6):602-610.
[27] WANG Y, MA F, JIN Z, et al. EANN: event adversarial neural networks for multi-modal fake news detection[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2018: 849-857.
[28] ZHANG X, CAO J, LI X, et al. Mining dual emotion for fake news detection[C]//Proceedings of the Web Conference, 2021: 3465-3476.
[29] ZHU H, KONIUSZ P. Simple spectral graph convolution[C]//Proceedings of the International Conference on Learning Representation, 2021: 151-163.
[30] POPAT K, MUKHERJEE S, YATES A, et al. Declare: debunking fake news and false claims using evidence-aware deep learning[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2018: 22-32.
[31] VO N, LEE K. Hierarchical multi-head attentive network for evidence-aware fake news detection[C]//Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics, 2021: 965-975.