Advertisement

User Identity Linkage Across Social Networks

  • Qifei LiuEmail author
  • Yanhui Du
  • Tianliang Lu
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 905)

Abstract

In order to distinguish the accounts that belong to the same person, we propose a method to link user identity across social networks based on user profile and relation. According to similarity calculation algorithms and network embedding, a feature extraction method in multi dimension was designed based on username, location, personal description, avatar and relation. Then a hierarchical cascaded machine learning model (HCML) is proposed to integrate the classifiers in different dimension. The experiment validates that the method in this paper outperforms feature extraction in single dimension, traditional machine learning algorithm and weighting algorithm. The method can be applied to integrate user information across social networks.

Keywords

User identity Across social networks User profile User relation 

Notes

Acknowledgement

This work was supported by the National Key R&D Program of China (2017YFB0802804), the National Natural Science Foundation of China (61602489).

References

  1. 1.
    Bartunov, S., Korshunov, A., Park, S., Ryu, W., Lee, H.: Joint link-attribute user identity resolution in online social networks categories and subject descriptors. In: Workshop on Social Network Mining and Analysis, pp. 104–109. ACM (2012)Google Scholar
  2. 2.
    Liu, J., Zhang, F., Song, X.Y., Song, Y., Lin, C.Y., Hon, H.W.: What is in a name? An unsupervised approach to link users across communities. In: ACM International Conference on Web Search and Data Mining, pp. 495–504. ACM (2013)Google Scholar
  3. 3.
    Zafarani, R., Lei, T., Huan, L.: User Identification across social media. ACM Trans. Knowl. Discov. Data 10(2), 1602–1630 (2015)CrossRefGoogle Scholar
  4. 4.
    Vosecky, J., Hong, D., Shen, V.Y.: User identification across multiple social networks. In: First International Conference on IEEE, pp. 360–365 (2009)Google Scholar
  5. 5.
    Wu, Z., Yu, H.T., Liu, S.R., Zhu, Y.H.: User identification across multiple social networks based on information entropy. J. Comput. Appl. 37(8), 2374–2380 (2017). (in Chinese)Google Scholar
  6. 6.
    Wang, Q., Shen, D.R., Feng, S., Kou, Y., Nie, T.Z., Yu, G.: Identifying users across social networks based on global view features with crowdsourcing. J. Softw. 29(3), 811–823 (2018). (in Chinese)Google Scholar
  7. 7.
    Liu, S., Wang, S., Zhu, F., Zhang, J., Krishnan, R.: HYDRA: large-scale social identity linkage via heterogeneous behavior modelling. In: ACM SIGMOD International Conference on Management of Data, pp. 51–62. ACM (2014)Google Scholar
  8. 8.
    Matt, J., Yu, S., Nicholas, I., Kilian, Q.: From word embeddings to document distances. In: International Conference on Machine Learning, pp. 957–966 (2015)Google Scholar
  9. 9.
    Tang, J., Qu, M., Wang, M., Zhang, M., Yan, J., Mei, Q.Z.: LINE: large-scale information network embedding. In: International World Wide Web Conferences Steering Committee, pp. 1067–1077. ACM (2015)Google Scholar
  10. 10.
    Maira, V., Carsten, E.: A cross-platform collection of social network profiles. In: ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 665–668. ACM (2016)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Information Technology and Network Security InstitutePeople’s Public Security University of ChinaBeijingChina
  2. 2.Collaborative Innovation Center of Security and Law for CyberspacePeople’s Public Security University of ChinaBeijingChina

Personalised recommendations