Online social media (OSM) has become a hotbed for the rapid dissemination of disinformation or faked news. In order to track and limit the spread of faked news, we study stance identification of comments posted on OSM, where the stance can denote the comment’s semantics. In this article, we propose a framework for identification of rumour stances, combining network topology and OSM comments. We construct a vector matrix of comments and words via OTI (optimisation term frequency–inverse document frequency). To better identify the stances, we introduce another vector matrix with novel or special attribute, that is, network topology among the users. Variant autoencoder (VAE) is then applied for dimensionality reduction and optimisation of these vector matrices which are then combined into an integrated matrix , tempered by two parameters and . Finally, the matrix is fed into a neural network for final rumour stance identification. Experimental evaluations show that our proposed approach outperforms some state-of-the-art methods and achieves a high precision of 90.26% and F1-score of 88.58%.
JiangCChenYLiuKJR. Graphical evolutionary game for information diffusion over social networks. IEEE J Sel Top Signal Process2014; 8(4): 524–536.
2.
LuoYMaJ. The influence of positive news on rumor spreading in social networks with scalefree characteristics. Int J Mod Phys C2018; 29(9): 1850078.
3.
LiangGHeWXuC, et al. Rumor identification in microblogging systems based on users behavior. IEEE Trans Comput Soc Syst2015; 2(3): 99–108.
4.
HuoLHuangPFangX. An interplay model for authorities’ actions and rumor spreading in emergency event. Phys A Stat Mech Appl2011; 390(20): 3267–3274.
5.
ZhuLZhaoHWangH. Complex dynamic behavior of a rumor propagation model with spatial-temporal diffusion terms. Inf Sci2016; 349–350: 119–136.
6.
ZubiagaAAkerABontchevaK, et al. Detection and resolution of rumours in social media: a survey. ACM Comput Surv2018; 51(2): 32.
7.
ZhangYChenWYeoCK, et al. Detecting rumors on online social networks using multi-layer autoencoder. In: 2017 IEEE technology engineering management conference (TEMSCON), Santa Clara, CA, 8–10 June 2017, pp. 437–441. New York: IEEE.
8.
LiuXNourbakhshALiQ, et al. Real-time rumor debunking on twitter. In: Proceedings of the 24th ACM international on conference on information and knowledge management, CIKM ’15, Melbourne, VIC, Australia, 19–23 October 2015, pp. 1867–1870. New York: ACM.
9.
MaJLuoY. The classification of rumour standpoints in online social network based on combinatorial classifiers. J Inf Sci2020; 46(2): 191–204.
10.
LiZXiongFWangX, et al. Topological influence-aware recommendation on social networks. Complexity2019; 3: 1–12.
11.
JinZCaoJGuoH, et al. Multimodal fusion with recurrent neural networks for rumor detection on microblogs. In: Proceedings of the 25th ACM international conference on multimedia, MM ’17, Nice, 21–25 October 2019, pp. 795–816. New York: ACM.
12.
ChoHBergerBPengJ. Compact integration of multi-network topology for functional analysis of genes. Cell Syst2016; 3(6): 540–548e5.
13.
RumelhartDHintonGWilliamsR. Learning representations by back-propagating errors. Nature1986; 323: 533–536.
14.
VincentPLarochelleHBengioY, et al. Extracting and composing robust features with denoising autoencoders. In: Proceedings of the 25th international conference on machine learning, ICML ’08, Helsinki, 5–9 July 2008, pp. 1096–1103. New York: ACM.
15.
VeysehAPBEbrahimiJDouD, et al. A temporal attentional model for rumor stance classification. In: Proceedings of the 2017 ACM on conference on information and knowledge management, CIKM ’17, Singapore, 6–10 November 2017, pp. 2335–2338. New York: ACM.
16.
LuoYMaJLiC. Entity name recognition of cross-border e-commerce commodity titles based on TWS-LSTM. Electron Commer Res2020; 20(2): 405–426.
17.
KumarASangwanSRNayyarA. Rumour veracity detection on twitter using particle swarm optimized shallow classifiers. Multimedia Tool Appl2019; 78(17): 24083–24101.
18.
ZubiagaAKochkinaELiakataM, et al. Discourse-aware rumour stance classification in social media using sequential classifiers. Inf Process Manage2018; 54(2): 273–290.
19.
KumarSCarleyK.Tree LSTMs with convolution units to predict stance and rumor veracity in social media conversations. In: Proceedings of the 57th annual meeting of the association for computational linguistics, Florence, 28July–2August2019, pp. 5047–5058. Stroudsburg, PA: Association for Computational Linguistics.
20.
LukasikMBontchevaKCohnT, et al. Gaussian processes for rumour stance classification in social media. ACM Trans Inf Syst2019; 37(2): 20.
21.
GroverALeskovecJ. Node2vec: scalable feature learning for networks. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, KDD ’16, San Francisco, CA, 13–17 August 2016, pp. 855–864. New York: ACM.
22.
PerozziBAl-RfouRSkienaS. Deepwalk: online learning of social representations. In: Proceedings of the 20th ACM SIGKDD international conference on knowledge discovery and data mining KDD ’14, Chicago, IL, 11–14 August 2013, pp. 701–710. New York: ACM.
23.
Lozano-DiezAZazoRToledanoDT, et al. An analysis of the influence of deep neural network (DNN) topology in bottleneck feature based language recognition. PLoS ONE2017; 12(8): 1–22.
24.
XiongFShenWChenH, et al. Exploiting implicit influence from information propagation for social recommendation. IEEE Trans Cybern2019; 2019: 1–14.
25.
QinMJinDLeiK, et al. Adaptive community detection incorporating topology and content in social networks. Knowl Based Syst2018; 161: 342–356.
26.
ZengKYuJWangR, et al. Coupled deep autoencoder for single image super-resolution. IEEE Trans Cybern2017; 47(1): 27–37.
27.
Xie YWangXJiangD, et al. High-performance community detection in social networks using a deep transitive autoencoder. Inf Sci2019; 493: 75–90.
28.
Al-QatfMLashengYAl-HabibM, et al. Deep learning approach combining sparse autoencoder with SVM for network intrusion detection. IEEE Access2018; 6: 52843–52856.
29.
ZhaoKJiangHLiX, et al. An optimal deep sparse autoencoder with gated recurrent unit for rolling bearing fault diagnosis. Meas Sci Technol2019; 31(1): 015005.
30.
YanBHanG. Effective feature extraction via stacked sparse autoencoder to improve intrusion detection system. IEEE Access2018; 6: 41238–41248.
31.
ChenWZhangYYeoCK, et al. Unsupervised rumor detection based on users’ behaviors using neural networks. Pattern Recognit Lett2018; 105: 226–233.
32.
WangWYuB. Text categorization based on combination of modified back propagation neural network and latent semantic analysis. Neural Comput Appl2008; 18(8): 875.
33.
XuYWangCDanZ, et al. Deep recurrent neural network and data filtering for rumor detection on Sina Weibo. Symmetry2019; 11(11): 1408.
34.
KuoRJTsengYSChenZY. Integration of fuzzy neural network and artificial immune system-based backpropagation neural network for sales forecasting using qualitative and quantitative data. J Intell Manuf2016; 27(6): 1191–1207.
35.
XiongFLiZY. Effective methods of restraining diffusion in terms of epidemic dynamics. Sci Rep2017; 7(1): 6013.
