全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

融合多特征的符号网络连边符号预测

DOI: 10.13190/j.jbupt.2014.05.017, PP. 80-84

Keywords: 符号网络,连边符号预测,社交网络分析,结构平衡理论

Full-Text   Cite this paper   Add to My Lib

Abstract:

为提高符号网络的连边符号预测准确率,深入分析了影响连边符号的各项基本机理,拓展了"结构平衡理论"和"地位理论",同时将网页网络中的"PageTrust"度量引入符号网络用以刻画符号网络中节点的重要性.在融合从不同角度反映连边符号形成机制理论的基础上,抽取出一组最能反映连边正负的网络特征,并将这类网络特征用于2类机器学习模型的训练与测试.2个真实网络数据集上的实验结果表明,训练所得模型具有较已有模型更高的预测准确率和更好的通用性.

References

[1]  Guha R, Kumar R, Raghavan P, et al. Propagation of trust and distrust[C]//Proceedings of the 13th International Conference on World Wide Web(WWW). USA: ACM Press, 2004: 403-412.
[2]  Kunegis J, Lommatzsch A, Bauckhage C. The slashdot zoo: mining a social network with negative edges[C]//Proceedings of the 18th International Conference on World Wide Web(WWW). ESP: ACM Press, 2009: 741-750.
[3]  Liu Haifeng, Lim E P, Lauw H W, et al. Predicting trusts among users of online communities: an epinions case study[C]//Proceedings of the 9th ACM Conference on Electronic Commerce. USA: ACM Press, 2008: 310-319.
[4]  Leskovec J, Huttenlocher D, Kleinberg J. Predicting positive and negative links in online social networks[C]//Proceedings of the 19th International Conference on World Wide Web(WWW). USA: ACM Press, 2010: 641-650.
[5]  Chiang K Y, Natarajan N, Tewari A, et al. Exploiting longer cycles for link prediction in signed networks[C]//Proceedings of the 20th ACM International Conference on Information and Knowledge Management(CIKM). USA: ACM Press, 2011: 1157-1162.
[6]  De Kerchove C, Van Dooren P. The PageTrust algorithm: how to rank web pages when negative links are allowed[C]//SIAM International Conference on Data Mining(SDM). USA: ACM Press, 2008: 346-352.
[7]  Chang Chihchung, Lin Chihjen. LIBSVM: a library for support vector machines[J]. ACM Transactions on Intelligent Systems and Technology, 2011, 2: 1-27.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133