ABSTRACT
Different social networks are independent of each other, and identifying the same person in different social networks is of great significance for cross-network information dissemination and the construction of a complete portrait of users. Existing methods for user identification via network embedding ignore the different contributions of neighbors and only consider low-order friend relationships. Aiming at these shortcomings, an algorithm of Network Embedding based on Multi-Orders Friends Contribution for User Identification (MOFC) is proposed. Firstly, the difference contribution degree of nodes to their friends is used to assign different weights to the edges between the nodes and their friends. Secondly, the embedding representation vectors of multi-orders friend contribution are used to describe the different orders friend relations of the nodes, and then the representation vectors of different orders are merged to more comprehensively represent network features. Finally, the fusion representation vectors are used as input sample of a neural network to train and build a user identification model. Experiments show that the evaluation indicators of the model have been significantly improved compared with several advanced methods. Compared with the newer and better the CSN_LINE, the accuracy rate of MOFC can be increased by 4.83%, the precision rate can be increased by 6.77%, the recall rate can be increased by 5.49%, the F1-score can be increased by 5.43%.
- Yuanhao Huang, Pengcheng Zhao, Qi Zhang, Ling Xing, Honghai Wu, and Huahong Ma. 2023. A Semantic-Enhancement-Based Social Network User-Alignment Algorithm. Entropy 25, 172(January 2023). https:// doi.org/10.3390/e25010172.Google ScholarCross Ref
- Tianliang Lei, Lixin Ji, Gengrun Wang, Shuxin Liu, Lan Wu, and Fei Pan. 2023. Transformer-Based User Alignment Model across Social Networks. electronics s 12, 1686(April 2023), https:// doi.org/10.3390/electronics12071686.Google ScholarCross Ref
- Cuicui Ye, Jing Yang, and Yan Mao. 2023. User identification for knowledge graph construction across multiple online social networks. Alexandria Engineering Journal 73 (May 2023), 145–158. https://doi.org/10.1016/j.aej.2023.04.035.Google ScholarCross Ref
- Liu Li, Zhang Youmin, Fu Shun, Zhong Fujin, Hu Jun, and Zhang Pu. 2019. ABNE: An Attention-Based Network Embedding for User Alignment Across Social Networks. IEEE Access 7 (2019) 23595-23605. https:// doi.org/10.1109/ACCESS.2019.2900095.Google ScholarCross Ref
- Zhang Guangsheng, Kang Zhao, and Tian Ling. 2023 User Identity Identification Technologies and Challenges for Network Security Governance. Journal of the University of Electronic Science and Technology of China 52, 3(May 2023), 398-412. https://doi.org/10.12178/1001-0548.2022106.Google ScholarCross Ref
- Zhu Rui, Zhao Yiming, Qu Wei, Liu Zhongyi, and Li Chenliang. 2022. Cross-Domain Product Search with Knowledge Graph. In Proceedings of the 31th ACM International Conference on Information and Knowledge Management. ACM, Atlanta, US, 3746-3755. https://doi.org/10.1145/3511808.3557116.Google ScholarDigital Library
- XING Ling, DENG Kai-kai, WU Hong-hai, and XIE Ping. 2020. A Survey of Cross-Social Network User Identity Recognition Research from the Perspective of Complex Networks. Journal of University of Electronic Science and Technology of China 49, 6(November 2020), 905-917. https://doi.org/10.12178/1001-0548.2019182Google ScholarCross Ref
- Zhang Yuxiang, Fu Jiamei, Yang Chengyi, and Xiao Chunjing. 2019. A local expansion propagation algorithm for social link identification. Knowledge and Information Systems, 60(2019), 545-568. https://doi.org/10.1007/s10115-018-1221-y.Google ScholarDigital Library
- Zhou Xiaoping, Liang Xun, Zhang Haiyan, and Ma Yuefeng. 2016. Cross-Platform Identification of Anonymous Identical Users in Multiple Social Media Networks. IEEE Transactions on Knowledge and Data Engineering 28, 2(February 2016), 411-424. https://doi.org/10.1109/TKDE.2015.2485222.Google ScholarDigital Library
- Jiajing Zhang, Zhenhua Yuan, Neng Xu, Jinlan Chen, and Juxiang Wang. 2021. Two-Stage User Identification Based on User Topology Dynamic Community Clustering. Complexity, Article ID 5567351 (July 2021), 1-10. https://doi.org/10.1155/2021/5567351.Google ScholarCross Ref
- Liu Qifei,Du Yanhui, and Lu Tianliang. 2020. User identity linkage across social network based on user relations. Application Research of Computers 37, 2 (February 2020), 381-384+406. https://doi.org/10.19734/j.issn.1001-3695.2018.07.0517.Google ScholarCross Ref
- Narayanan Arvind, and Shmatikov Vitaly.2009.De-anonymizing social networks. In Proceedings of the 30th IEEE Symposium on Security and Privacy (IEEE SSP), IEEE, Oakland, US, 173–187. https://doi.org/10.1109/SP.2009.22.Google ScholarDigital Library
- Cui Yi, Pei, Jian, Tang Guanting, Luk Wo-Shun, Jiang Daxin, and Hua Ming. 2013. Finding email correspondents in online social networks. World Wide Web 16, 2(March 2013), 195-218. https://doi.org/10.1007/s11280-012-0168-2.Google ScholarDigital Library
- Kong Xiangnan, Zhang Jiawei, and Yu, Philip S. 2013. Inferring anchor links across multiple heterogeneous social networks. In Proceedings of the 22nd ACM international conference on Information and Knowledge Management (CIKM) , ACM, San Francisco, US, 179-188. https://doi.org/10.1145/2505515.2505531.Google ScholarDigital Library
- Tan Shulong, Guan Ziyu, Cai Deng, Qin Xuzhen, Bu Jiajun, and Chen Chun. 2014. Mapping users across networks by Manifold Alignment on Hypergraph. In Proceedings of the 28th National Conference on Artificial Intelligence (NCAI), AAAI, Phuket, Thailand, v1, 159-165.Google Scholar
- Xu Qian, Chen Hongchang, Wu Zheng, and Huang Ruiyang. 2017. User identification method across social networks based on weighted hypergraph. Journal of Computer Applications 37, 12(December 2017), 3435-3441+3471. https://doi.org/10.11772/j.issn.1001-9081.2017.12.3435.Google ScholarCross Ref
- Wu Zheng, Yu Hongtao, Huang Ruiyang, and Liu Shuxin. 2018. User identification across multiple networks based on hidden label nodes mining. Application Research of Computers 35, 4(April 2018), 1191–1196. https://doi.org/10.3969 /j.issn.1001-3695.2018. 04.049.Google Scholar
- Liu Li, Cheung William K, Li Xin, and Liao Lejian. 2016. Aligning Users across Social Networks Using Network Embedding. In Proceedings of the 25th International Joint Conference on Artificial Intelligence (IJCAI), IJCAI, New York, US, 1774-1780. https://www.researchgate.net/publication/326551541.Google Scholar
- Man Tong, Shen Huawei, Liu Shenghua, Jin Xiaolong, and Cheng Xueqi. 2016. Predict anchor links across social networks via an embedding approach. In Proceedings of the 25th International Joint Conference on Artificial Intelligence (IJCAI), IJCAI, New York, US, 1823-1829.Google Scholar
- Cao Shaosheng, Lu Wei, and Xu Qiongkai. GraRep: Learning Graph Representations with Global Structural Information. In Proceedings of the 24th ACM international on conference on information and knowledge management(CIKM), ACM, Melbourne, Australia, 891-900. https://doi.org/10.1145/2806416.2806512.Google ScholarDigital Library
- Britta Ruhnau. Eigenvector-centrality-a node-centrality? Social networks 22, 4(October 2000), 357-365. https://doi.org/10.1016/S0378-733(00)00031-9.Google ScholarCross Ref
- Tang Jian, Qu Meng, Wang Mingzhe, Zhang Ming, Yan Jun, and Mei Qiaozhu. 2015. Line: Large-scale information network embedding. In Proceedings of the 24th International Conference of World Wide Web (WWW), Springer-Verlag, Florence, Italy, 1067-1077. https://doi.org/10.1145/2736277.2741093.Google ScholarDigital Library
- Gutmann, Michael U. and Hyvärinen Aapo. 2012. Noise-Contrastive Estimation of Unnormalized Statistical Models with Applications to Natural Image Statistics. Journal of Machine Learning Research, 13(February 2012), 07–361.Google Scholar
- Zhang Jiawei, and Yu Philip S.. 2015. Integrated anchor and social link predictions across social networks. In Proceedings of the 24th International Joint Conference on Artificial Intelligence (IJCAI) , IJCAI, Buenos Aires, Argentina, 2125-2131.Google Scholar
- Perozzi Bryan, Al-Rfou Rami and Skiena Steven. DeepWalk: online learning of social representations, In Proceedings of the 20th ACM Conference on Knowledge Discovery and Data Mining (SIGKDD) ,ACM, New York, US, 701-710. https://doi.org/10.1145/2623330.2623732.Google ScholarDigital Library
- Grover Aditya, and Leskovec Jure. node2vec: Scalable feature learning for networks. In Proceedings of the 22nd ACM Conference on Knowledge Discovery and Data Mining (SIGKDD) , ACM, San Francisco, US, 855-864. https://doi.org/10.1145/2939672.2939754.Google ScholarDigital Library
Index Terms
- MOFC: Network Embedding Based on Multi-Orders Friends Contribution for User Identification
Recommendations
Exploiting similarities of user friendship networks across social networks for user identification
Highlights- All our feature analyses and experiments are conducted on the ground-truth datasets.
- The distributions of features on the positive instances and the negative instances are different.
- The features related to the 1-hop neighbors ...
AbstractUser identification has been attracting considerable attention from academia. Due to the uniqueness and difficulty of faking friendship networks, some friendship-based methods have been presented to improve the identification performance. However,...
Multi-network User Identification via Graph-Aware Embedding
Advances in Knowledge Discovery and Data MiningAbstractUser identification is widely used in anomaly detection, recommendation system and so on. Previous approaches focus on extraction of features describing users, and the learners try to emphasize the differences between different user identities. ...
Incremental User Identification Across Social Networks Based on User-Guider Similarity Index
AbstractIdentifying accounts across different online social networks that belong to the same user has attracted extensive attentions. However, existing techniques rely on given user seeds and ignore the dynamic changes of online social networks, which ...
Comments