Mining user behavior patterns in social networks is of great importance in user behavior analysis, targeted marketing, churn prediction and other applications. However, less effort has been made to study the evolution of user behavior in social communities. In particular, users join and leave communities over time. How to automatically detect the online community transitions of individual users is a research problem of immense practical value yet with great technical challenges. In this paper, we propose an algorithm based on the Minimum Description Length (MDL) principle to trace the evolution of community transition of individual users, adaptive to the noisy behavior. Experiments on real data sets demonstrate the efficiency and effectiveness of our proposed method.
Lecture Notes in Computer Science: 7th International Symposium, Sagt 2014, Haifa, Israel, September 30 – October 2, 2014. Proceedings, 2014, p. 231-243
Main Research Area:
Lecture Notes in Computer Science
Symposium on Algorithmic Game TheorySymposium on Algorithmic Game Theory, 2014