Algorithm research for user trajectory matching across social media networks based on paragraph2vec

Identifying users across different social media networks (SMN) is to link accounts of the same user that belong to the same individual across SMNs. The problem is fundamental and important, and its results can benefit many applications such as cross SMN user modeling and recommendation. With the development of GPS technology and mobile communication, more and more social networks provide location services. This provides a new opportunity for cross SMN user identification. In this paper, we solve cross SMN user identification problem in an unsupervised manner by utilizing user trajectory data in SMNs. A paragraph2vec based algorithm is proposed in which location sequence feature of user trajectory is captured in temporal and spatial dimensions. Our experimental results validate the effectiveness and efficiency of our algorithm.

[1]  Dawei Zhao,et al.  Linking social network accounts by modeling user spatiotemporal habits , 2017, 2017 IEEE International Conference on Intelligence and Security Informatics (ISI).

[2]  Xing Xie,et al.  Mining user similarity based on location history , 2008, GIS '08.

[3]  Yang Liu,et al.  Semantic analysis of spatial temporal trajectory in LBSNs , 2017 .

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

[5]  Shou-De Lin,et al.  Matching users and items across domains to improve the recommendation quality , 2014, KDD.

[6]  Wei Cao,et al.  Automatic user identification method across heterogeneous mobility data sources , 2016, 2016 IEEE 32nd International Conference on Data Engineering (ICDE).

[7]  Naveen Nandan.  A Grid-Based Approach for Similarity Mining of Massive Geospatial Trajectories , 2014, 2014 IEEE International Conference on Computer and Information Technology.

[8]  Longbo Huang,et al.  User identification in cyber-physical space: a case study on mobile query logs and trajectories , 2016, SIGSPATIAL/GIS.

[9]  Albert-László Barabási,et al.  Understanding individual human mobility patterns , 2008, Nature.

[10]  Xing Xie,et al.  GeoLife: A Collaborative Social Networking Service among User, Location and Trajectory , 2010, IEEE Data Eng. Bull..

[11]  Heng Tao Shen,et al.  Searching trajectories by locations: an efficiency study , 2010, SIGMOD Conference.

[12]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

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

[14]  Silvio Lattanzi,et al.  Linking Users Across Domains with Location Data: Theory and Validation , 2016, WWW.

[15]  Lianhai Wang,et al.  Social Media account linkage using user-generated geo-location data , 2016, 2016 IEEE Conference on Intelligence and Security Informatics (ISI).

[16]  Yong Yu,et al.  Joint User Modeling across Aligned Heterogeneous Sites , 2016, RecSys.