基于多层次深度模型的社交网络核心谣言传播节点识别

doi:10.7523/j.ucas.2022.057

摘要/Abstract

摘要： 鉴于在线社交网络谣言控制的时效性与及时性，提出一种基于多维特征的两阶段图卷积网络(MSF-GCN)学习模型。该模型试图在尽早的时间实现精准定位核心谣言传播节点，从源头上阻断谣言扩散。通过将MSF-GCN方法与其他基准方法在谣言数据集上进行比对，实验结果验证了MSF-GCN学习模型更加有效。

关键词: 在线社交网络, 谣言, 识别核心节点, 图卷积神经网络

Abstract: Online social networks have become the disaster areas where rumors grow. It is of great significance to identify core rumor spreaders for rumor prevention and control. The traditional rumor control model is mainly based on the dynamics of rumor propagation, and it is mainly focused on in-event or post-event control. In view of the timeliness of rumor control, this paper proposes a multi-stage graph convolutional network based on multi-dimensional features (MSF-GCN) deep learning model to accurately locate core rumor spreaders as early as possible and block rumor diffusion from the source. This work compares the MSF-GCN method with other three baseline methods on rumor data set, and the experimental results verify that our method is more efficient.

Key words: online social network, rumor, identify core nodes, GCN

中图分类号:

TP181

李元, 张栖, 朱建明, 焦建彬. 基于多层次深度模型的社交网络核心谣言传播节点识别[J]. 中国科学院大学学报, 2024, 41(1): 136-144.

LI Yuan, ZHANG Qi, ZHU Jianming, JIAO Jianbin. Identification of core rumor spreaders in online social networks based on multi-stage deep model[J]. Journal of University of Chinese Academy of Sciences, 2024, 41(1): 136-144.

参考文献

[1] DiFonzo N, Bordia P. Rumor psychology: social and organizational approaches[M]. Washington: American Psychological Association, 2007. DOI: 10.1037/11503-000.
[2] Kwak H, Lee C, Park H, et al. What is Twitter, a social network or a news media?[C]//Proceedings of the 19th International Conference on World Wide Web-WWW’10. April 26-30, 2010. Raleigh, North Carolina, USA. New York: ACM Press, 2010: DOI:10.1145/1772690.1772751.
[3] Vosoughi S, Roy D, Aral S. The spread of true and false news online[J]. Science, 2018, 359(6380): 1146-1151. DOI:10.1126/science.aap9559.
[4] Hosni A I E, Li K. Minimizing the influence of rumors during breaking news events in online social networks[J]. Knowledge-Based Systems, 2020, 193: 105452. DOI:10.1016/j.knosys.2019.105452.
[5] Tong G A, Wu W L, Guo L, et al. An efficient randomized algorithm for rumor blocking in online social networks[J]. IEEE Transactions on Network Science and Engineering, IEEE, 7(2): 845-854. 2020, DOI:10.1109/TNSE.2017.2783190.
[6] Zhu J M, Ni P K, Wang G Q. Activity minimization of misinformation influence in online social networks[J]. IEEE Transactions on Computational Social Systems, 2020, 7(4): 897-906. DOI:10.1109/TCSS.2020.2997188.
[7] Kimura M, Saito K, Motoda H. Blocking links to minimize contamination spread in a social network[J]. ACM Transactions on Knowledge Discovery from Data, 2009, 3(2): 9. DOI:10.1145/1514888.1514892.
[8] Nandi A K, Medal H R. Methods for removing links in a network to minimize the spread of infections[J]. Computers & Operations Research, 2016, 69: 10-24. DOI:10.1016/j.cor.2015.11.001.
[9] Budak C, Agrawal D, El Abbadi A. Limiting the spread of misinformation in social networks[C]//Proceedings of the 20th International Conference on World Wide Web-WWW'11. March 28-April 1, 2011. Hyderabad, India. New York: ACM Press, 2011: DOI:10.1145/1963405.1963499.
[10] Zhu J M, Ghosh S, Wu W L. Robust rumor blocking problem with uncertain rumor sources in social networks[J]. World Wide Web, 2021, 24(1): 229-247. DOI: 10.1007/s11280-020-00841-8.
[11] Hosni A I E, Li K, Ahmad S. DARIM: dynamic approach for rumor influence minimization in online social networks[C]//Neural Information Processing, 2019: 619-630. DOI: 10.1007/978-3-030-36711-4_52.
[12] Wang Y, Cong G, Song G J, et al. Community-based greedy algorithm for mining top-k influential nodes in mobile social networks[C]//KDD’10: Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2010: 1039-1048. DOI:10.1145/1835804.1835935.
[13] Kempe D, Kleinberg J, Tardos É. Maximizing the spread of influence through a social network[C]//KDD’03: Proceedings of the Ninth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2003: 137-146. DOI:10.1145/956750.956769.
[14] Leskovec J, Krause A, Guestrin C, et al. Cost-effective outbreak detection in networks[C]//KDD’07: Proceedings of the 13th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2007: 420-429. DOI:10.1145/1281192.1281239.
[15] Chen W, Wang Y J, Yang S Y. Efficient influence maximization in social networks[C]//KDD’09: Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2009: 199-208. DOI:10.1145/1557019.1557047.
[16] Ilyas M U, Radha H. Identifying influential nodes in online social networks using principal component centrality[C]//2011 IEEE International Conference on Communications. June 5-9, 2011, Kyoto, Japan. IEEE, 2011: 1-5. DOI:10.1109/icc.2011.5963147.
[17] Ma Q, Ma J. Identifying and ranking influential spreaders in complex networks with consideration of spreading probability[J]. Physica A: Statistical Mechanics and Its Applications, 2017, 465: 312-330. DOI:10.1016/j.physa.2016.08.041.
[18] Lv Z W, Zhao N, Xiong F, et al. A novel measure of identifying influential nodes in complex networks[J]. Physica A: Statistical Mechanics and Its Applications, 2019, 523: 488-497. DOI:10.1016/j.physa.2019.01.136.
[19] Benevenuto F, Magno G, Rodrigues T, et al. Detecting spammers on twitter[C]//Seventh annual Collaboration, Electronic messaging, Anti-Abuse and Spam Conference July 13-14, 2010, Redmond, Washington, US. 2010: DOI:10.1.1.297.5340.
[20] Gupta A, Kaushal R. Towards detecting fake user accounts in facebook[C]//2017 ISEA Asia Security and Privacy-ISEASP. January 29-February 1, 2017, Surat, India. IEEE, 2017: 1-6. DOI:10.1109/ISEASP.2017.7976996.
[21] Kitsak M, Gallos L K, Havlin S, et al. Identification of influential spreaders in complex networks[J]. Nature Physics, 2010, 6(11): 888-893. DOI: 10.1038/nphys1746.
[22] Agha Mohammad Ali Kermani M, Badiee A, Aliahmadi A, et al. Introducing a procedure for developing a novel centrality measure (sociability centrality) for social networks using TOPSIS method and genetic algorithm[J]. Computers in Human Behavior, 2016, 56: 295-305. DOI:10.1016/j.chb.2015.11.008.
[23] Dewi F K, Yudhoatmojo S B, Budi I. Identification of opinion leader on rumor spreading in online social network twitter using edge weighting and centrality measure weighting[C]//2017 Twelfth International Conference on Digital Information Management (ICDIM). September 12-14, 2017, Fukuoka, Japan. IEEE, 2017: 313-318. DOI:10.1109/ICDIM.2017.8244680.
[24] Cai J, Luo J W, Wang S L, et al. Feature selection in machine learning: a new perspective[J]. Neurocomputing, 2018, 300: 70-79. DOI:10.1016/j.neucom.2017.11.077.
[25] Inuwa-Dutse I, Liptrott M, Korkontzelos I. Detection of Spam-posting accounts on twitter[J]. Neurocomputing, 2018, 315: 496-511. DOI: 10.1016/j.neucom.2018.07.044.
[26] Zheng X H, Zeng Z P, Chen Z Y, et al. Detecting spammers on social networks[J]. Neurocomputing, 2015, 159: 27-34. DOI:10.1016/j.neucom.2015.02.047.
[27] Qu C Q, Zhan X X, Wang G H, et al. Temporal information gathering process for node ranking in time-varying networks[J]. Chaos (Woodbury, N.Y.), 2019, 29(3): 033116. DOI:10.1063/1.5086059.
[28] Hamilton W L, Ying R, Leskovec J. Representation learning on graphs: methods and applications [EB/OL]. arXiv:1709.05584. (2017-09-17) [2018-04-10]. https://arxiv.org/abs/1709.05584.
[29] Zhang M H, Chen Y X. Link prediction based on graph neural networks [EB/OL]. arXiv:1802.09691. (2018-02-27) [2018-12-03]. https://arxiv.org/abs1802.09691.
[30] Yu E Y, Wang Y P, Fu Y, et al. Identifying critical nodes in complex networks via graph convolutional networks[J]. Knowledge-Based Systems, 2020, 198: 105893. DOI:10.1016/j.knosys.2020.105893.
[31] Zhao G H, Jia P, Zhou A M, et al. InfGCN: identifying influential nodes in complex networks with graph convolutional networks[J]. Neurocomputing, 2020, 414: 18-26. DOI:10.1016/j.neucom.2020.07.028.
[32] Xiao Y P, Yang Q F, Sang C Y, et al. Rumor diffusion model based on representation learning and anti-rumor[J]. IEEE Transactions on Network and Service Management, 2020, 17(3): 1910-1923. DOI:10.1109/TNSM.2020.2994141.
[33] Zhang J, Liu B, Tang J, et al. Social influence locality for modeling retweeting behaviors[C]//IJCAI’13: Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence. August 01 2013, Beijing, China. 2013: 2761-2767.
[34] Hinton G E, Srivastava N, Krizhevsky A, et al. Improving neural networks by preventing co-adaptation of feature detectors [EB/OL]. arXiv:1207.0580. (2012-07-03) [2017-07-03]. https://arxiv.org/abs1207.0580.
[35] Kingma D P, Ba J, Adam: a method for stochastic optimization [EB/OL]. arXiv:1412.6980. (2014-12-22) [2017-01-30]. https://arxiv.org/abs1412.6980.
[36] Prechelt L. Early stopping-but when? [M]//Lecture Notes in Computer Science. Berlin, Heidelberg: Springer Berlin Heidelberg, 1998: 55-69. DOI:10.1007/3-540-49430-8_3.
[37] Rumelhart D E, Hinton G E, Williams R J. Learning representations by back-propagating errors[J]. Nature, 1986, 323(6088): 533-536. DOI:10.1038/323533a0.
[38] Wang G S. A survey on training algorithms for support vector machine classifiers[C]//2008 Fourth International Conference on Networked Computing and Advanced Information Management. September 2-4, 2008, Gyeongju, Korea (South). IEEE, 2008: 123-128. DOI:10.1109/NCM.2008.103.
[39] Liao Y H, Vemuri V R. Use of K-nearest neighbor classifier for intrusion detection[J]. Computers & Security, 2002, 21(5): 439-448. DOI:10.1016/S0167-4048(02)00514-X.
[40] Menard S. Standards for standardized logistic regression coefficients[J]. Social Forces, 2011, 89(4): 1409-1428. DOI:10.1093/sf/89.4.1409.