Heterogeneous Behavior for Public Identity
AUTHORS
NageswaraRao Moparthi,1100-100 Department of Computer Science and Engineering, Velagapudi Ramakrishna Siddhartha Engineering College, Vijayawada, AP
ABSTRACT
Social identity linkage across wholly totally different social media platforms is of essential importance to business intelligence by gaining from social data a deeper understanding and lots of correct identification of users. throughout this paper, we have a tendency to tend to propose a solution framework, HYDRA, that consists of three key steps: (I) we have a tendency to tend to model heterogeneous behavior by long (II) we have a tendency to tend to make structure consistency models to maximise the structure and behavior consistency on users’ core system across wholly totally different platforms, therefore the task of identity linkage could also be performed on groups of users, that's on the way facet the individual level linkage in previous study; and (III) we have a tendency to tend to propose a normalized- margin-based linkage operate formulation, and learn the linkage operate by multi-objective optimization where every supervised pair-wise linkage operate learning and structure consistency maximization ar conducted towards a unified social scientist optimum resolution. The model is in a position to influence forceful data missing, and avoid the curse- of-dimensionality in handling high dimensional thin illustration. intensive experiments on ten million users across seven standard social networks platforms demonstrate that HYDRA properly identifies real user linkage across totally different platforms from large wheezy user behavior information records, and outperforms existing progressive approaches by a minimum of 2 hundredth below totally different settings, and four times higher in most settings..
KEYWORDS
Organization, HYDRA, Pairwise, Linkage, Consistancy.
REFERENCES
[1] J. Liu, F. Zhang, X. Song, Y.I. Song, C.Y. Lin, and H. W. Hon, “What’s in a name?: Anunsupervised approach to link users across communities”.
[2] R. Zafarani, and H. Liu, “Connecting users across social media sites: A behavioral-modelingapproach”.
[3] S. Kumar, R. Zafarani, and H. Liu, “Understanding user migration patterns in social media”.
[4] R. Zheng, J. Li, H. Chen, and Z. Huang, “A framework for authorship identification of online messages: Writingstyle features and classification techniques”.
[5] O. Hassanzadeh, K.Q. Pu, S.H. Yeganeh, R. J. Miller, M. Hernandez, L. Popa, and H. Ho, “Discovering linkage points over web data”.
[6] S. Liu, S. Wang, and Feida Zhu, “Structured Learning from Heterogeneous Behavior for Social Identity Linkage”, IEEE Transactions on Knowledge and Data Engineering, Vol. 27, No. 7, (2015).
[7] T. Iofciu, P. Fankhauser, F. Abel, and K. Bischoff, “Identifying users across social taggingsystems”, In: ICWSM’11, (2011).
[8] J. Liu, F. Zhang, X. Song, Y.I. Song, C.Y. Lin, and H.W. Hon, “What’s in a name ?: An unsupervised approach to link users across communities”, In: WSDM’13, (2013).
[9] R. Zafarani, and H Liu, “Connecting users across social media sites: A behavioral-modelingapproach”, In: KDD’13, (2013).
[10] O. deVel, A. Anderson, M. Corney, and G. Mohay, “Mining e-mail content for author identification forensics”, SIGMOD Record, Vol. 30, No. 4, pp. 55-64, (2001).