Dynamic communities and their detection

摘要: Overlapping community detection has already become an interesting problem in data mining and also a useful technique applications. This underlines the importance of following lifetime communities real graphs. Palla et al. developed promising method, analyzed evolution on two large databases [23]. We have followed their footsteps analyzing real-world found, that framework they use to describe dynamics is insufficient for our data. The method used by dependent very special algorithm, clique percolation its monotonic nature. In this paper we propose extension basic events described [23] capable handling found nonmonotonic algorithm. report findings came from tests social