Social network analysis is a discipline that has emerged to analyze social structures and information networks to uncover patterns of interaction among the vertices in the network. Most social networks are dynamic, and studying the evolution of these networks over time could provide insight into the behavior of individuals expressed by the nodes in the graph and the flow of information among them. In a dynamic network, communities, which are groups of densely interconnected nodes, are affected by changes in the underlying population. The analysis of communities and their evolutions can help determine the shifting structural properties of the networks. We present a framework for modeling and detecting community evolution over time. First, our proposed community matching algorithm efficiently identifies and tracks similar communities over time. Then, a series of significant events and transitions are defined to characterize the evolution of networks in terms of its communities and individuals. We also propose two metrics called stability and influence metrics to describe the active behavior of the individuals. We present experiments to explore the dynamics of communities on the Enron email and DBLP datasets. Evaluating the events using topics extracted from the detected communities demonstrates that we can successfully track communities over time in real datasets.

No abstract

No abstract

We present our novel community mining algorithm that uses only local information to accurately identify communities, outliers, and hubs in social networks. The main component of our algorithm is the T metric, which evaluates the relative quality of a community by considering the number of internal and external triads (3-node cliques) it contains. Furthermore we propose an intuitive statistical method based on our T metric, which correctly identifies outlier and hub nodes within each discovered community. Finally, we evaluate our approach on a series of groundtruth networks and show that our method outperforms the state-of-the-art in community mining algorithms.

We present our COMmunity Boundary (COMB) and COMmunity Circles (COMC) network layout algorithms that focus on revealing the structure of discovered communities and the relationships between these communities. We believe this information is vital when developing new community mining algorithms as it allows the viewer to more quickly assess the quality of a mining result without appealing to large tables of statistics. To implement our algorithms we have introduced numerous modifications to the existing Fruchterman-Reingold layout, including support for multi-sized vertices, removal of the bounding frame, introduction of circular bounding boxes, and a novel slotting system. Our evaluation argues that both COMB and COMC outperform existing alternatives in their ability to reveal community structure and emphasize inter-community relations.