Behavioral Modeling in Social Networks: From Micro to Macro
Tutorial in the the 15th IEEE International Conference on Data Mining (ICDM)
2:00PM - 5:00PM on Tuesday, November 17, 2015 (TUTORIAL - III)
Room Marlborough C, Bally's Atlantic City Hotel, Atlantic City, NJ, U.S.A.
Tutors
Meng Jiang is a Postdoctoral Researcher in University of Illinois at Urbana-Champaign. His research area include social media analysis and behavioral modeling. He focuses on social recommendation and suspicious behavior detection. He obtained his Ph.D. in 2015 from Department of Computer Science and Technology at Tsinghua University. He visited the Database Group of Carnegie Mellon University in 2012-2013. He published over ten papers in major journals and conferences of data mining, and received the 2014 ACM SIGKDD Best Paper Finalist.
Peng Cui is an Assistant Professor in Tsinghua University. His research area include social network analysis and social multimedia computing. He focuses more on user behavior analysis, user influence mining and information diffusion tracing and prediction. In 2015, he was honored with ACM China Rising Star Award. He obtained his Ph.D. in 2009 from Tsinghua University and joined the Department in 2012. He published over 50 papers in data mining and multimedia computing, and received three best paper awards including the 2015 ICDM Best Student Paper Award.
Abstract
The development of social networks has enabled the collection of behavioral data of unprecedented size and complexity. Modern social platforms have realized that great scientific and marketing values are contained in the millions of billions of behavioral records. How can we model users' behaviors in social networks? What are the concepts and principles in modeling the complex behaviors? Can we develop efficient models for accurate behavior prediction and detection in social applications such as recommender systems, personalized search and social marketing? In this tutorial, we answer these questions by uncovering the social and spatiotemporal contextual dependency, cross-domain and cross-platform properties, synchronized and abnormal characteristics, and many other patterns of users' behaviors. We introduce recent advances in modeling complex behaviors from the perspectives of individuals, groups and cascades (from micro to macro) in social networks. Finally we summarize the tutorial with discussions on open issues and challenges about behavior modeling in social networks.
Schedule
| Time | Duration | Content | Question |
|---|---|---|---|
| 2:00PM | 20min | Introduction | What is behavioral modeling in social networks? Is it useful? |
| 2:20PM | 40min | Modeling individual behavior I | How to model behavior with social and spatiotemporal contexts? |
| 3:00PM | 20min | Modeling individual behavior II | How to model cross-domain behavior in social networks? |
| 3:20PM | 20min | Break | Social time! |
| 3:40PM | 40min | Modeling cascading behavior | How to model information diffusion for tracing and prediction? |
| 4:20PM | 30min | Detecting suspicious behavior | How to detect suspicious behavior in social networks (socia fraud)? |
| 4:50PM | 10min | Take away and QA | Summary, open issues and challenges, discussions of the field. |