Refreshments will be served.
Retweeting is one of the most important features in microblogging such as Twitter and Sina Weibo. The retweeting mechanism empowers users to spread their messages beyond the reach of the original tweet’s followers. In this talk, we are focused on three fundamental questions that can help illustrate how information dynamically flows through a social media network.
1. Why do followers have different retweeting behaviors?
2. How to accurately predict the number of times that a particular message posted by one specific user will be retweeted across the network?
3. What distribution (single burst or multi-peaks) do a message’s retweets follow in its life cycle, single burst or multi-peaks?
We will present our proposed solutions of these three problems and show our observations and preliminary evaluations on Sina Weibo datasets. We will discuss how they potentially connect to customer analytics in various domains such as retail. If time further permits, we will also briefly show our spectral graph analysis approach and its use in community partition, influential node identification, and anomaly detection from network topology.
Dr. Xintao Wu is a Professor of Software and Information Systems Department and leads Data Privacy Research Lab at UNC Charlotte. His major research interests include data mining, data privacy and security, and most recently social media analysis. Dr. Wu got his Ph.D. in Information Technology from George Mason University in 2001. He received his BS degree in Information Science from the University of Science and Technology of China in 1994, and ME degree in Computer Engineering from the Chinese Academy of Space Technology in 1997. Dr. Wu serves on three editor boards of journals and numerous program committees of international conferences in his research fields. He is a recipient of NSF CAREER Award (2006), Excellence in Undergraduate Teaching Award (2005), and Outstanding Faculty Research Award (2009) from College of Computing and Informatics.