Zip-OSN: Towards Building Time Capsule for Online Social Activities

depth-2 cascade graph Online social networking sites such as Facebook, LinkedIn, and Twitter allow users to seek out friends or colleagues and interact with them in novel ways. At the same time, user-generated content has mushroomed in a collaborative manner in multiple contexts, e.g., online reviews of services/products, Wikipedia, and open software development. This new ecosystem of content generation, sharing, consumption, and innovation has completely reshaped the web by making it more of a massive online social system. This has huge implications on information propagation, consumer behavior and market economics (e.g., online rating/recommendations), as well as political behavior (e.g., 2011-12 uprisings in the Middle East).

Being able to preserve, model, and predict information cascades over online social networks will have many theoretical and practical implications, e.g., for marketing, recommendation filtering, and studying of societal behavior. Massive empirical data sets on users' online social activities are being collected, but they are often too big to analyze. Our grand vision is to build a time capsule that can condense pertinent information about online social activities (derived from massive data from multiple sources) as user interactions evolve through time. Such digests should be compact enough to store and process, yet contain rich enough information to support a wide range of queries or hypothesis testings in future. Towards this end, we propose to analyze online social activities by studying the associated user activity graphs (UAGs), in which a node represents a user, and an edge represents a specific action. Our goal is to design graph generative models and summarization techniques that can preserve pertinent information about these UAGs, including macro-level dynamic growth/evolution of the graphs, as well as micro-level user influence in the recruitment process. In addition, the project will design graph summarization techniques that preserve pertinent information to answer a common set of queries, such as identifying the most "collectively influential" users.

We will build on some of the results and insights gained in our earlier OSN project on measuring and characterizing large-scale online social networks and applications.

People

Faculty

Collaborators

  • Ashwin Aravindakshan, Graduate School of Management, UC Davis
  • Balachander Krishnamurthy, AT&T Labs-Research
  • Stratis Ioannidis, previously at Technicolor Palo Alto Lab
  • Yong-Jae Lee, Computer Science, UC Davis

Postdoctoral Researcher

  • Jinyoung Han (currently Assistant Professor at Hanyang University, Korea)

Graduate Students

  • Ehsan Gholami, ECE (PhD)
  • Kevin Manuel, CS (CS)

Alumni

  • Han Liu, ECE (PhD, 2014)
  • Mohammad Rezaur Rahman, CS (PhD, 2015)
  • (Sally) Yiwei Sun, ECE (MS, 2015)
  • Theo Pan, CS (MS, 2015)
  • Zejun Huang, ECE (MS, 2015)
  • Ali Emara, CS (MS, 2016)
  • Jingyu Zhang, ECE (MS, 2016)
  • Aditi Garg, CS (MS, 2017)
  • Janis Fredrick, CS (MS, 2017)
  • Devika Joshi, CS (MS, 2017)
  • Deepika Chandrasekaran (MS, 2018)

Undergrads

  • Jiaming Xie

Publications

  • W. Hu, K. Singh, F. Xiao, J. Han, C-N. Chuah, and Y. J. Lee, "Who Will Share My Image? Predicting the Content Diffusion Path in Online Social Networks," ACM International Conference on Web Search and Data Mining (WSDM), Feb 2018.
  • L. Gong, L. Huang, P. Tune, J. Han, C-N. Chuah, M. Roughan, and J. Xu, “ForestStream: Accurate Measurement of Cascades in Online Social Networks,” IEEE ICCCN, July/Aug 2017.
  • J. Han, D. Choi, J. Joo, and C-N. Chuah, "Predicting Popular and Viral Image Cascades in Pinterest," AAAI Conference on Web and Social Media (ICWSM), May 2017.
  • M. R. Rahman, J. Han, and C-N. Chuah, "Analyzing the Adoption and Cascading Process of OSN-based Gifting Applications: An Empirical Study," ACM Transactions on Web, vol. 11, no. 2, Article #10, April 2017.
  • H. Liu, S. Ioannidis, S. Bhagat, and C-N. Chuah, "Adding Structure: Social Network Inference with Graph Priors," ACM SIGKDD Workshop on Mining and Learning with Graphs, August 2016.
  • J. Han, D. Choi, A-Y. Choi, J. Choi, T. Chung, T. T. Kwon, J-Y. Rha, C-N. Chuah, "Sharing Topics in Pinterest: Understanding Content Creation and Diffusion Behaviors," to appear in ACM Conference on Online Social Networks (COSN), November 2015.
  • V. Vijayaraghavan, P-A Noel, Z. Maoz, R. M. D'Souza, "Quantifying correlated edge dynamics in co-evolving multiplex networks", accepted to Scientific Reports, May 2015. [Preprint]
  • M. R. Rahman, J. Han, and C-N. Chuah, "Unveiling the Adoption and Cascading Process of OSN-based Gifting Applications," IEEE INFOCOM, April 2015. [pdf]
  • M. R. Rahman, C-N. Chuah, "Can Sampling Preserve Application Adoption Process of OSN Graphs?" Abstract & Poster, NetSci, June 2-6 2014. [pdf]
  • M. R. Rahman, P-A. Noel, C-N. Chuah, B. Krishnamurthy, and R. M. D'Souza, "Peeking into Invitation-based Adoption Process of OSN-based Applications," ACM Computer Communication Review (CCR), vol. 44, no. 1, pp. 21-27, January 2014. (Best of CCR, to be presented at ACM SIGCOMM 2014) [pdf]
  • H. Liu, A. Nazir, J. Joung, and C-N. Chuah, "Modeling/ Predicting the Evolution of User Activity Graphs on OSN-based Applications," WWW, May 2013. [pdf]

Thesis/Reports

  • A. Garg, Predicting User Engagement on University Facebook Pages, M.S. Project Report, Computer Science, UC Davis, 2017.
  • D. Joshi, Characterizing the Political Strategies of US Election 2016 and the Effects on User Response, M.S. Project Report, Computer Science, UC Davis, 2017
  • J. Fredick, Brand Prediction using Community Detection on Demographic Information and Purchasing Behavior of Consumers, M.S. Project Report, Computer Science, UC Davis, 2017
  • A. Emara, Inferring Mobile Applications Usage among Different Demographics, MS thesis, Computer Science, UC Davis, 2016.
  • J. Zhang, Uncovering Synergistic Business Relationship through Online User Reviews, M.S. Report, ECE, UC Davis, 2016
  • Z. Huang, Analyzing Social Interactions and Relationships in OSN -based Gifting Applications, M.S. Report, ECE, UC Davis, 2015.
  • T. T. Pan, Interest Meets Pinterest: Identifying Important User Roles in Content Propagation, M.S. Thesis, Computer Science, UC Davis, 2015.
  • Y. Sun, Data-Driven Prediction of Online Social Network Process, M.S. Project Report, Electrical & Computer Engineering, UC Davis, 2015
  • M. R. Rahman, Characterizing and Predicting Information Diffusion through Social Interactions, PhD dissertation, Computer Science, UC Davis, March 2015.
  • H. Liu, Measuring and Modeling the Cascades/Diffusions through Online Social Networks, PhD dissertation, Electrical & Computer Engineering, UC Davis, 2014.

See more publications from our previous OSN project here.

Funding

This project is supported by National Science Foundation CNS-1302691 grant (2013-2018).