Characterizing User Connections in Social Media through User-Shared Images

Billions of user images, which are shared on social media, can be widely accessible by others due to their sharing nature. Using machine-generated labels to annotate those images is a reliable for user connections discovery on social networks. The machine-generated labels are obtained from encoded vectors using up-to-date image processing and computer vision techniques, such as convolution neural network. By analyzing 2 million user-shared images from 8 online social networks, a phenomenon is observed that the distribution of user similarity based on their shared images follows exponential functions. Users who share visually similar images are likely having follower/followee relationships, regardless of the origins and the content sharing mechanisms of a social network. This phenomenon is nicely formulated for a multimedia big data recommendation engine as an alternative to social graphs for recommendation. By utilizing the formulation of the distribution, it is proven the proposed engine can be 46 percent better than previous approaches in <inline-formula><tex-math notation="LaTeX">$F1$</tex-math><alternatives> <inline-graphic xlink:href="cheung-ieq1-2762719.gif"/></alternatives></inline-formula> score and achieves a comparable performance of friends-of-friends approach. To the best of our knowledge, this is the first attempt in related fields to characterize such phenomenon by massive user-shared images collected from real-world SNs, and then formulate into practical analytics engine for connection discovery.

[1]  Michael J. Swain,et al.  Color indexing , 1991, International Journal of Computer Vision.

[2]  Xing Xie,et al.  Potential Friend Recommendation in Online Social Network , 2010, 2010 IEEE/ACM Int'l Conference on Green Computing and Communications & Int'l Conference on Cyber, Physical and Social Computing.

[3]  Alexander J. Smola,et al.  Like like alike: joint friendship and interest propagation in social networks , 2011, WWW.

[4]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[5]  James She,et al.  Connection Discovery Using Big Data of User-Shared Images in Social Media , 2015, IEEE Transactions on Multimedia.

[6]  David G. Lowe,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004, International Journal of Computer Vision.

[7]  Tim Weninger,et al.  Collaborative and Structural Recommendation of Friends using Weblog-based Social Network Analysis , 2006, AAAI Spring Symposium: Computational Approaches to Analyzing Weblogs.

[8]  Xin Li,et al.  Tag-based social interest discovery , 2008, WWW.

[9]  Bamshad Mobasher,et al.  Personalized recommendation in social tagging systems using hierarchical clustering , 2008, RecSys '08.

[10]  Jennifer Neville,et al.  Using Transactional Information to Predict Link Strength in Online Social Networks , 2009, ICWSM.

[11]  M Girvan,et al.  Structure of growing social networks. , 2001, Physical review. E, Statistical, nonlinear, and soft matter physics.

[12]  James She,et al.  Non-user Generated Annotation on User Shared Images for Connection Discovery , 2015, 2015 IEEE International Conference on Data Science and Data Intensive Systems.

[13]  Eric Gilbert,et al.  Predicting tie strength with social media , 2009, CHI.

[14]  Scott A. Golder,et al.  Structural Predictors of Tie Formation in Twitter: Transitivity and Mutuality , 2010, 2010 IEEE Second International Conference on Social Computing.

[15]  Krishna P. Gummadi,et al.  Measurement and analysis of online social networks , 2007, IMC '07.

[16]  Linyuan Lu,et al.  Link Prediction in Complex Networks: A Survey , 2010, ArXiv.

[17]  Charles Elkan,et al.  Link Prediction via Matrix Factorization , 2011, ECML/PKDD.

[18]  B. S. Manjunath,et al.  Not all tags are created equal: Learning flickr tag semantics for global annotation , 2009, 2009 IEEE International Conference on Multimedia and Expo.

[19]  Michael R. Lyu,et al.  UserRec: A User Recommendation Framework in Social Tagging Systems , 2010, AAAI.

[20]  James She,et al.  An Efficient Computation Framework for Connection Discovery using Shared Images , 2017, ACM Trans. Multim. Comput. Commun. Appl..

[21]  Xiaoming Zhang,et al.  Social image tagging using graph-based reinforcement on multi-type interrelated objects , 2013, Signal Process..

[22]  W. S. Chow,et al.  Social network, social trust and shared goals in organizational knowledge sharing , 2008, Inf. Manag..

[23]  Cordelia Schmid,et al.  Evaluation of GIST descriptors for web-scale image search , 2009, CIVR '09.

[24]  Antonio Torralba,et al.  Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope , 2001, International Journal of Computer Vision.

[25]  Rushed Kanawati,et al.  Link Prediction in Complex Networks , 2020, Cognitive Analytics.

[26]  C. D. Kemp,et al.  Density Estimation for Statistics and Data Analysis , 1987 .

[27]  James She,et al.  Evaluating the Privacy Risk of User-Shared Images , 2016, ACM Trans. Multim. Comput. Commun. Appl..

[28]  Chi-Yin Chow,et al.  iGSLR: personalized geo-social location recommendation: a kernel density estimation approach , 2013, SIGSPATIAL/GIS.

[29]  Jorge J. Moré,et al.  Computing a Trust Region Step , 1983 .

[30]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[31]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[32]  Jure Leskovec,et al.  Friendship and mobility: user movement in location-based social networks , 2011, KDD.

[33]  Yoshua Bengio,et al.  Pattern Recognition and Neural Networks , 1995 .

[34]  Andrew Zisserman,et al.  Return of the Devil in the Details: Delving Deep into Convolutional Nets , 2014, BMVC.

[35]  Ido Guy,et al.  Personalized recommendation of social software items based on social relations , 2009, RecSys '09.

[36]  Michael J. Muller,et al.  Make new friends, but keep the old: recommending people on social networking sites , 2009, CHI.