传播树结构结点及路径双注意力谣言检测模型

doi:10.11896/jsjkx.220200037

计算机科学 ›› 2023, Vol. 50 ›› Issue (4): 22-31.doi: 10.11896/jsjkx.220200037

• 数据库&大数据&数据科学 • 上一篇下一篇

传播树结构结点及路径双注意力谣言检测模型

韩雪明^1,2, 贾彩燕^1,2, 李轩涯³, 张鹏飞^1,2

1 北京交通大学计算机与信息技术学院北京 100044
2 北京交通大学交通数据分析与挖掘北京市重点实验室北京 100044
3 百度在线网络技术(北京)有限公司北京 100085

收稿日期:2022-02-08 修回日期:2022-05-12 出版日期:2023-04-15 发布日期:2023-04-06
通讯作者: 贾彩燕(cyjia@bjtu.edu.cn)
作者简介:(xueminghan@bjtu.edu.cn)
基金资助:
国家重点研发计划(2017YFC1703506);国家自然科学基金(61876016);中央高校基本科研业务费专项资金(2019JBZll0);百度松果计划开放研究基金

Dual-attention Network Model on Propagation Tree Structures for Rumor Detection

HAN Xueming^1,2, JIA Caiyan^1,2, LI Xuanya³, ZHANG Pengfei^1,2

1 School of Computer and Information Technology,Beijing Jiaotong University,Beijing 100044,China
2 Beijing Key Lab of Traffic Data Analysis and Mining,Beijing Jiaotong University,Beijing 100044,China
3 Baidu Online Network Technology(Beijing)Co.,Ltd.,Beijing 100085,China

Received:2022-02-08 Revised:2022-05-12 Online:2023-04-15 Published:2023-04-06
About author:HAN Xueming,born in 1998,postgra-duate.His main research interests include natural language processing and rumor detection.
JIA Caiyan,born in 1976,Ph.D,professor.Her main research interests include data mining,social computing and natural language processing.
Supported by:
National Key R&D Program of China(2017YFC1703506),National Natural Science Foundation of China(61876016),Fundamental Research Funds for the Central Universities(2019JBZll0) and Open Research Fund of Baidu Pinecone Program.

摘要/Abstract

摘要： 随着社交媒体平台的快速发展和移动设备的普及,人与人之间的交互变得更加便捷。但同时,谣言在社交媒体上也更加肆虐,给公众和社会安全带来巨大的隐患。在现实世界中,用户在发表自己的评论之前,往往会首先观测其他已经发表的帖子,尤其是即将评论的帖子上下文。现有的一些谣言检测方法虽然使用了谣言传播过程中的传播结构,基于群体智能原则提取用户间的相互质疑或事实线索,极大地提高了谣言检测的效果,但是对传播结构的深层非直接隐式关系及关键帖子和关键路径重要性的学习能力不足。据此,文中提出了一种基于传播树的结点及路径双注意力谣言检测模型DAN-Tree( Dual-attention Network Model on Propagation Tree Structures)。该模型使用Transformer结构学习传播路径中帖子间的隐式语义关系,并利用注意力机制学习路径中结点的重要度;其次,利用注意力机制对路径表示进行加权聚合得到整个传播树的表示向量;最后,基于传播树表示向量进行谣言分类。此外,我们使用结构嵌入方法学习帖子在传播树上的空间位置信息,进一步对谣言传播结构上的深层结构和语义信息进行融合。在4个经典数据集上的实验结果表明:DAN-Tree模型在其中的3个数据集上都超过了目前已有文献的最优结果。在Twitter15和Twitter16数据集上正确率指标分别提升了1.81%和2.39%,在PHEME数据集上F₁指标提升了7.51%。

关键词: 谣言检测, 传播结构, 注意力机制, 社交媒体, 深度学习

Abstract: With the rapid development of social media and the popularity of mobile devices,the interaction between users has become more convenient.But at the same time,rumors on social media are more and more rampant,which brings hidden dangers to the public and social safety.In the real world,users often express their own opinions after observing other microblogs that have been posted,especially the context of the microblog to be replied.Although some existing rumor detection methods learn the propagation patterns on propagation trees of rumors to extract clues of user interrogation or factual evidences based on the principle of crowd wisdom,which greatly improves the performance of rumor detection,they only focus on those microblogs that have direct response relationships,and Lack of ability to fully mine the indirect and implicit relationships among microblogs in the process of rumor propagation.Therefore,in this paper,a node and path dual-attention network on propagation tree structures(DAN-Tree) for debunking rumors is proposed.First,the model uses the Transformer structure to fully learn the implicit semantic relationship between posts in the propagation path,and then uses the attention mechanism to perform weighted fusion to obtain the feature vector of the propagation path.Secondly,the path representation is weighted and aggregated by using the attention mechanism to obtain the representation vector of the whole propagation tree.In addition,the structure embedding method is used to learn the spatial location information of the post on the propagation tree,which realizes the effective fusion of the deep structure and semantic information in the rumor propagation structure.The effect of the DAN-Tree model is verified on four classic datasets.Experimental results show that the DAN-Tree model surpasses the best results of the existing literature on the three datasets:the accuracy of the Twitter15 and Twitter16 datasets increases by 1.81% and 2.39%,respectively,and the F₁ score of the PHEME dataset increases by 7.51%,which proves the effectiveness of DAN-Tree model.

Key words: Rumor detection, Propagation structure, Attention mechanism, Social media, Deep learning

中图分类号:

TP181

韩雪明, 贾彩燕, 李轩涯, 张鹏飞. 传播树结构结点及路径双注意力谣言检测模型[J]. 计算机科学, 2023, 50(4): 22-31. https://doi.org/10.11896/jsjkx.220200037

HAN Xueming, JIA Caiyan, LI Xuanya, ZHANG Pengfei. Dual-attention Network Model on Propagation Tree Structures for Rumor Detection[J]. Computer Science, 2023, 50(4): 22-31. https://doi.org/10.11896/jsjkx.220200037

参考文献

[1]CHEN Y F,LI Z Y,LIANG X,et al.Review onrumor detection of online social networks[J].Chinese Journal of Computers,2018,41(7):1648-1676.
[2]ZUBIAGA A,AKER A,BONTCHEVA K,et al.Detection and resolution of rumours in social media:a survey[J].ACM Computing Surveys,2018,51(2):1-36.
[3]MA J,GAO W,WONG K F.Detect rumors in microblog posts using propagation structure via kernel learning[C]//Procee-dings of the 55th Annual Meeting of the Association for Computational Linguistics.Stroudsburg:ACL,2017:708-717.
[4]WU K,YANG S,ZHU K Q.False rumors detection on sinaweibo by propagation structures[C]//Proceedings of the 31st IEEE International Conference on Data Engineering.New York:IEEE,2015:651-662.
[5]MA J,GAO W,WONG K F.Rumor detection on twitter with tree-structured recursive neural networks[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics.Stroudsburg,PA:ACL,2018:1980-1989.
[6]BIAN T,XIAO X,XU T Y,et al.Rumor detection on social media with bi-directional graph convolutional networks[C]//Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence.Menlo Park,CA:AAAI,2020:549-556.
[7]VASWANI A,SHAZEER N,PARMAR N,et al.Attention isall you need[C]//Proceedings of the 31st International Confe-rence on Neural Information Processing Systems.New York:Curran Associates,2017:6000-6010.
[8]NGUYEN X P,JOTY S,HOI A,et al.Tree-structured attention with hierarchical accumulation[C]//Proceedings of the 8th International Conference on Learning Representations.OpenReview.net,2020.
[9]DAI Z H,YANG Z L,YANG Y M,et al.Transformer-xl:attentive language models beyond a fixed-length context[C]//Proceedings of the 57th Conference of the Association for Computational Linguistics.Stroudsburg,PA:ACL,2019:2978-2988.
[10]RAFFEL C,SHAZEER N,ROBERTS A,et al.Exploring the limits of transfer learning with a unified text-to-text transformer[J].Journal of Machine Learning Research,2020,21:1-67.
[11]KHOO L M S,CHIEU H L,QIAN Z,et al.Interpretable rumor detection in microblogs by attending to user interactions[C]//Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence.Menlo Park,CA:AAAI,2020:8783-8790.
[12]ZHAO Z,RESNICK P,MEI Q Z.Enquiring minds:early detection of rumors in social media from enquiry posts[C]//Procee-dings of the 24th International Conference on World Wide Web.New York:ACM,2015:1395-1405.
[13]CASTILLO C,MENDOZA M,POBLETE B.Information credibility on twitter[C]//Proceedings of the 20th International Conference on World Wide Web.New York:ACM,2011:675-684.
[14]KWON S,CHA M,JUNG K.Prominent features of rumorpropagation in online social media[C]//Proceedings of the 13th International Conference on Data Mining.New York:IEEE,2013:1103-1108.
[15]MA J,GAO W,WEI Z Y,et al.Detect rumors using time series of social contextinformation on microblogging websites[C]//Proceedings of the 24th ACM International Conference on Information and Knowledge Management.New York:ACM,2015:1751-1754.
[16]YANG F,YU X H,LIU Y,et al.Automatic detection of rumor on sina weibo[C]//Proceedings of the ACM SIGKDD Workshop on Mining Data Semantics.New York:ACM,2012:1-7.
[17]LIAO X W,HUANG Z,YANG D D,et al.Rumor detection in social media based on a hierarchical attention network[J].SCIENTIA SINICA Informationis,2018,48:1558-1574.
[18]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.Menlo Park,CA:AAAI,2016:3818-3824.
[19]YU F,LIU Q,WU S,et al.A convolutional approach for misinformation identification[C]//Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence.ijcai.org,2017:3901-3907.
[20]LIU Y,WU Y F B.Early detection of fake news on social media through propagation path classification with recurrent and con-volutional networks[C]//Proceedings of the Thirty-second AAAI Conference on Artificial Intelligence.Palo Alto,CA:AAAI,2018:354-361.
[21]GUO H,CAO J,ZHANG Y Z,et al.Rumor detection with hie-rarchical social attention network[C]//Proceedings of the 27th ACM International Conference on Information and Knowledge Management.New York:ACM,2018:943-951.
[22]YUAN C Y,MA Q W,ZHOU W,et al.Jointly embedding the local and global relations of heterogeneous graph for rumor detection[C]//Proceedings of the 2019 IEEE International Confe-rence on Data Mining(ICDM).New York:IEEE,2019:796-805.
[23]KUMAR S,CARLEY K M.Tree lstms with convolution unitsto predict stance and rumor veracity in social media conversations[C]//Proceedings of the 57th Conference of the Association for Computational Linguistics.Stroudsburg,PA:ACL,2019:5047-5058.
[24]MA J,GAO W,JOTY S R,et al.An attention-based rumor detection model with tree-structured recursiveneural networks[J].ACM Transactions on Intelligent Systems and Technology(TIST),2020,11(4):1-28.
[25]MA J,GAO W.Debunking rumors on twitter with tree transformer[C]//Proceedings of the 28th International Conference on Computational Linguistics.ICCL,2020:5455-5466.
[26]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,PA:ACL,2019:4171-4186.
[27]YANG L,WANG P,LI H,et al.A holistic representationguided attention network for scene text recognition[J].Neurocomputing,2020,414:67-75.
[28]YU D L,LI X,ZHANG C Q,et al.Towards accurate scene textrecognition with semantic reasoning networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE,2020:12110-12119.
[29]KINGMA D P,BA J.Adam:a method for stochastic optimization[C]//Proceedings of the 3rd International Conference on Learning Representations.2015.
[30]ZUBIAGA A,LIAKATA M,PROCTER R,et al.Analysinghow people orient to and spread rumours in social media by looking at conversational threads[J].PloS one,2016,11(3):e0150989.
[31]DUCHI J,HAZAN E,SINGER Y.Adaptive subgradient me-thods for online learning and stochastic optimization[J].Journal of Machine Learning Research,2011,12(7):2121-2159.

相关文章 15

[1]	雪峰豪, 蒋海波, 唐聃. 深度学习在健康医疗中的应用研究综述 Review of Deep Learning Applications in Healthcare 计算机科学, 2023, 50(4): 1-15. https://doi.org/10.11896/jsjkx.220600166
[2]	尹恒, 张凡, 李天瑞. 基于多邻接图与多头注意力机制的短期交通流量预测 Short-time Traffic Flow Forecasting Based on Multi-adjacent Graph and Multi-head Attention Mechanism 计算机科学, 2023, 50(4): 40-46. https://doi.org/10.11896/jsjkx.220200079
[3]	雒晓辉, 吴云, 王晨星, 余文婷. 基于用户长短期偏好的序列推荐模型 Sequential Recommendation Model Based on User’s Long and Short Term Preference 计算机科学, 2023, 50(4): 47-55. https://doi.org/10.11896/jsjkx.220100264
[4]	王娅丽, 张凡, 余增, 李天瑞. 基于交互注意力和图卷积网络的方面级情感分析 Aspect-level Sentiment Classification Based on Interactive Attention and Graph Convolutional Network 计算机科学, 2023, 50(4): 196-203. https://doi.org/10.11896/jsjkx.220100105
[5]	刘泽润, 郑红, 邱俊杰. 基于抽象语法树裁剪的智能合约漏洞检测研究 Smart Contract Vulnerability Detection Based on Abstract Syntax Tree Pruning 计算机科学, 2023, 50(4): 317-322. https://doi.org/10.11896/jsjkx.220300063
[6]	于兴崭, 芦天亮, 杜彦辉, 王曦锐, 杨成. 基于合成图像和Xception改进模型的安卓恶意家族分类方法 Android Malware Family Classification Method Based on Synthetic Image and Xception Improved Model 计算机科学, 2023, 50(4): 351-358. https://doi.org/10.11896/jsjkx.220300200
[7]	李帅, 徐彬, 韩祎珂, 廖同鑫. SS-GCN:情感增强和句法增强的方面级情感分析模型 SS-GCN:Aspect-based Sentiment Analysis Model with Affective Enhancement and Syntactic Enhancement 计算机科学, 2023, 50(3): 3-11. https://doi.org/10.11896/jsjkx.220700238
[8]	陈富强, 寇嘉敏, 苏利敏, 李克. 基于图神经网络的多信息优化实体对齐模型 Multi-information Optimized Entity Alignment Model Based on Graph Neural Network 计算机科学, 2023, 50(3): 34-41. https://doi.org/10.11896/jsjkx.220700242
[9]	周明强, 代开浪, 吴全旺, 朱庆生. 异构信息网络的注意力感知多通道图卷积评分预测模型 Attention-aware Multi-channel Graph Convolutional Rating Prediction Model for Heterogeneous Information Networks 计算机科学, 2023, 50(3): 129-138. https://doi.org/10.11896/jsjkx.220300004
[10]	董永峰, 黄港, 薛婉若, 李林昊. 融合IRT的图注意力深度知识追踪模型 Graph Attention Deep Knowledge Tracing Model Integrated with IRT 计算机科学, 2023, 50(3): 173-180. https://doi.org/10.11896/jsjkx.211200134
[11]	华晓凤, 冯娜, 于俊清, 何云峰. 基于规则推理的足球视频任意球射门事件检测 Shooting Event Detection of Free Kick in Soccer Video Based on Rule Reasoning 计算机科学, 2023, 50(3): 181-190. https://doi.org/10.11896/jsjkx.220300062
[12]	梅鹏程, 杨吉斌, 张强, 黄翔. 一种基于三维卷积的声学事件联合估计方法 Sound Event Joint Estimation Method Based on Three-dimension Convolution 计算机科学, 2023, 50(3): 191-198. https://doi.org/10.11896/jsjkx.220500259
[13]	白雪飞, 马亚楠, 王文剑. 基于特征融合的边缘引导乳腺超声图像分割方法 Segmentation Method of Edge-guided Breast Ultrasound Images Based on Feature Fusion 计算机科学, 2023, 50(3): 199-207. https://doi.org/10.11896/jsjkx.211200294
[14]	刘航, 普园媛, 吕大华, 赵征鹏, 徐丹, 钱文华. 极化自注意力约束颜色溢出的图像自动上色 Polarized Self-attention Constrains Color Overflow in Automatic Coloring of Image 计算机科学, 2023, 50(3): 208-215. https://doi.org/10.11896/jsjkx.220100149
[15]	陈亮, 王璐, 李生春, 刘昌宏. 基于深度学习的可视化仪表板生成技术研究 Study on Visual Dashboard Generation Technology Based on Deep Learning 计算机科学, 2023, 50(3): 238-245. https://doi.org/10.11896/jsjkx.230100064

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

传播树结构结点及路径双注意力谣言检测模型

Dual-attention Network Model on Propagation Tree Structures for Rumor Detection

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 0