Balancing User Profile and Social Network Structure for Anchor Link Inferring Across Multiple Online Social Networks

Along with the popularity of online social network (OSN), more and more OSN users tend to create their accounts in different OSN platforms. Under such circumstances, identifying the same user among different OSNs offers tremendous opportunities for many applications, such as user identification, migration patterns, influence estimation, and expert finding in social media. Different from existing solutions which employ user profile or social network structure alone, in this paper, we proposed a novel joint solution named MapMe, which takes both user profile and social network structure feature into account, so that it can adapt more OSNs with more accurate results. MapMe first calculates user similarity via profile features with the Doc2vec method. Then, it evaluates user similarity by analyzing user’s ego network features. Finally, the profile features and ego network features were combined to measure the similarity of the users. Consequently, MapMe balances the two similarity factors to achieve goals in different platforms and scenarios. Finally, experiments are conducted on the synthetic and real data sets, proving that MapMe outperforms the existing methods with 10% on average.

[1]  Pang-Ning Tan,et al.  A framework for joint community detection across multiple related networks , 2012, Neurocomputing.

[2]  Xiaolong Jin,et al.  Predict Anchor Links across Social Networks via an Embedding Approach , 2016, IJCAI.

[3]  Vitaly Shmatikov,et al.  Myths and fallacies of "Personally Identifiable Information" , 2010, Commun. ACM.

[4]  NarayananArvind,et al.  Myths and fallacies of "Personally Identifiable Information" , 2010 .

[5]  Jure Leskovec,et al.  The dynamics of viral marketing , 2005, EC '06.

[6]  Paul Erdös,et al.  On random graphs, I , 1959 .

[7]  Virgílio A. F. Almeida,et al.  Studying User Footprints in Different Online Social Networks , 2012, 2012 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining.

[8]  Philip S. Yu,et al.  Partial Network Alignment with Anchor Meta Path and Truncated Generic Stable Matching , 2015, ArXiv.

[9]  Claude Castelluccia,et al.  How Unique and Traceable Are Usernames? , 2011, PETS.

[10]  Ramayya Krishnan,et al.  HYDRA: large-scale social identity linkage via heterogeneous behavior modeling , 2014, SIGMOD Conference.

[11]  Danai Koutra,et al.  BIG-ALIGN: Fast Bipartite Graph Alignment , 2013, 2013 IEEE 13th International Conference on Data Mining.

[12]  Derong Shen,et al.  Anchor Link Prediction Using Topological Information in Social Networks , 2016, WAIM.

[13]  Phillip Bonacich,et al.  Some unique properties of eigenvector centrality , 2007, Soc. Networks.

[14]  John Skvoretz,et al.  Node centrality in weighted networks: Generalizing degree and shortest paths , 2010, Soc. Networks.

[15]  Reza Zafarani,et al.  Connecting Corresponding Identities across Communities , 2009, ICWSM.

[16]  Reza Zafarani,et al.  Connecting users across social media sites: a behavioral-modeling approach , 2013, KDD.

[17]  Sree Hari Krishnan Parthasarathi,et al.  Exploiting innocuous activity for correlating users across sites , 2013, WWW.

[18]  Peter Fankhauser,et al.  Identifying Users Across Social Tagging Systems , 2011, ICWSM.

[19]  Jian Pei,et al.  Finding email correspondents in online social networks , 2013, World Wide Web.

[20]  Xiaoping Zhou,et al.  Cross-Platform Identification of Anonymous Identical Users in Multiple Social Media Networks , 2016, IEEE Transactions on Knowledge and Data Engineering.

[21]  Xiang Zhu,et al.  Identifying users across social networks based on dynamic core interests , 2016, Neurocomputing.

[22]  Z. Di,et al.  Clustering coefficient and community structure of bipartite networks , 2007, 0710.0117.

[23]  Charu C. Aggarwal,et al.  Link prediction across networks by biased cross-network sampling , 2013, 2013 IEEE 29th International Conference on Data Engineering (ICDE).

[24]  Vitaly Shmatikov,et al.  De-anonymizing Social Networks , 2009, 2009 30th IEEE Symposium on Security and Privacy.

[25]  Philip S. Yu,et al.  COSNET: Connecting Heterogeneous Social Networks with Local and Global Consistency , 2015, KDD.

[26]  Ping Zhu,et al.  A study of graph spectra for comparing graphs and trees , 2008, Pattern Recognit..

[27]  Tao Zhou,et al.  Solving the cold-start problem in recommender systems with social tags , 2010 .

[28]  Jie Tang.  AMiner: Mining Deep Knowledge from Big Scholar Data , 2016, WWW.

[29]  Philip S. Yu,et al.  Multiple Anonymized Social Networks Alignment , 2015, 2015 IEEE International Conference on Data Mining.

[30]  Mohammad Al Hasan,et al.  A Survey of Link Prediction in Social Networks , 2011, Social Network Data Analytics.

[31]  Reza Zafarani,et al.  User Identification Across Social Media , 2015, ACM Trans. Knowl. Discov. Data.

[32]  Philip S. Yu,et al.  Inferring anchor links across multiple heterogeneous social networks , 2013, CIKM.

[33]  William W. Cohen,et al.  A Comparison of String Metrics for Matching Names and Records , 2003 .

[34]  Virgílio A. F. Almeida,et al.  Characterizing user behavior in online social networks , 2009, IMC '09.

[35]  Duncan J. Watts,et al.  Collective dynamics of ‘small-world’ networks , 1998, Nature.

[36]  Albert,et al.  Emergence of scaling in random networks , 1999, Science.

[37]  Lada A. Adamic,et al.  Search in Power-Law Networks , 2001, Physical review. E, Statistical, nonlinear, and soft matter physics.

[38]  Chun Chen,et al.  Mapping Users across Networks by Manifold Alignment on Hypergraph , 2014, AAAI.

[39]  M E J Newman,et al.  Community structure in social and biological networks , 2001, Proceedings of the National Academy of Sciences of the United States of America.

[40]  Quoc V. Le,et al.  Distributed Representations of Sentences and Documents , 2014, ICML.

[41]  Jason J. Jung,et al.  ACO-based clustering for Ego Network analysis , 2017, Future Gener. Comput. Syst..

[42]  Fan Zhang,et al.  What's in a name?: an unsupervised approach to link users across communities , 2013, WSDM.