随着网络和通信技术的发展,谣言借助微博等平台可快速扩散,形成病毒式传播,给国家安全和社会稳定造成严重的安全隐患。为了提高谣言自动检测的准确率,对基于图注意力网络的全局-局部注意力编码谣言检测模型进行了改进。首先,引入用户属性信息对微博文本内容特征和传播结构特征进行补充,得到更高阶特征;其次,改进图注意力机制以得到更健壮的节点聚合特征,为判决是否为谣言提供更准确的依据。在微博谣言数据集上的实验结果表明,相对于已有算法,该文提出的检测模型具有更高的检测准确率。
Abstract
With the development of network and communication technology, rumors spread rapidly like virus with in Weibo and other platforms, causing serious risks to national security and social stability. In order to improve the accuracy of automatic rumor detection, we present a global-local attention network for rumor detection model. Firstly, user features are introduced as higher-order features in addition to the text information and propagation structure features of Weibo. Secondly, the graph attention network is improved to obtain more robust node aggregation features, which provides more accurate evidence for judging a rumor. The experimental results on the Weibo rumor dataset show that the detection model proposed in this paper has higher accuracy than the existing algorithms.
关键词
谣言检测 /
图注意力机制 /
用户属性信息 /
传播结构信息
{{custom_keyword}} /
Key words
rumor detection /
graph attention network /
user features /
structure propagation information
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 让·诺埃尔·卡普费雷. 谣言: 世界上最古老的传媒[M]. 郑若麟,译. 上海: 上海人民出版,2008: 53-54.
[2] SHU K, SLIVA A, WANG S, TANG J L,et al. Fake news detection on social media: A data mining perspective[J]. ACM SIGKDD Exploration Newsletter,2017,19(1): 22-36.
[3] ZHOU X Y, ZAFARANI R. A survey of fake news: Fundamental theories, detection methods, and opportunities[J]. ACM Computing Surveys,2020,53(5): 1-40.
[4] QAZVINIAN V, ROSENGREN E, RADEV D R,et al. Rumorhas it: Identifying misinformation in microblogs[C]//Proceedings of the Conference on Empirical Method sin Natural Language Processing.Scotland,UK:Association for Computational Linguistics,2011: 1589-1599.
[5] CASTILLO C, MENDOZA M, POBLET B. Information credibility on Twitter[C]//Proceedings of the 20th International Conference on World Wide Web.Hyderabad,India:ACM,2011: 675-684.
[6] LIANG G, HE W B, XU C,et al. Rumor identification in microblogging systems based on users’behavior[J]. IEEE Transactions on Computational Social Systems,2015,2(3): 99-108.
[7] MENDOZA M, POBLET B, CASTILLO C. Twitter under crisis:can we trust what we RT?[C]//Proceedings of the 1st Workshop on Social Media Analytics. Washington,USA:ACM,2010: 71-79.
[8] 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,New York,USA:AAAIPress, 2016: 3818-3824.
[9] AJAO O,BHOWMIK D,ZARGARI S.Fake news identification on twitter with hybrid CNN and RNN models[C]//Proceedings of the 9th International Conferenceon Social Media and Society,USA:ACM,2018: 226-230.
[10] RUCHANSKY N, SEO S, LIU Y.CSI: A hybrid deep model for fake news detection[C]//Proceedings of CIKM,2017: 797-806.
[11] XU N, CHEN G D, MAO W J. MNRD: A merged neural model for rumor detection in social media[C]//Proceedings of the International Joint Conference on Neural Networks,2018: 885-891.
[12] LIAO X, HUANG Z, YANG D,et al. Rumor detection insocial media based on a hierarchical attention network[J].Scientia Sinica Information,2018,48(11): 1558-1574.
[13] BIAN T, XIAO X, XU T Y,et al. Rumor detection on social media with bi-direction graph convolutionalnetworks[C]//Proceedings of the 34th AAAI Conference on Artificial Intelligence,2020: 549-556.
[14] 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 19th IEEE International Conference on DataMining, China,2019: 796-805.
[15] VELICKOVIC P, CUCURULL G, CASANOVA A, et al.Graph attention networks[C]//Proceedings of the International Conference on Learning Representations,2018:arXiv:1710.10903v3, 2018.
[16] BRODY S,ALON U, YAHAV E.How Attentive are Graph Attention Networks?[J]. arXiv 2021:2105.14491v2, 2021.
[17] SONG C, TU C,YANG C,et al.CED: Credible early detectionof social media rumors[J]. IEEE Transaction Knowledge and Data Engineering,2021,33(3): 3035-3047.
[18] YANG F,LIU Y,YU X,et al.Automatic detection of rumoron sina weibo[C]//Proceedings of the ACM SIGKDD Workshop on Mining Data Semantics,China:ACM,2012: 13-20.
[19] LIU Y, WU Y F.Early detection of fake news on social media through propagation path classification with recurrent and convolutional networks[C]//Proceedings of the 32nd AAAI Conference on Artificial Intelligence,USA,2018: 354-361.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金(61521003)
{{custom_fund}}
PDF(1735 KB)
