Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining
A framework for community identification in dynamic social networks
Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining
An event-based framework for characterizing the evolutionary behavior of interaction graphs
Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining
Tracking the Evolution of Communities in Dynamic Social Networks
ASONAM '10 Proceedings of the 2010 International Conference on Advances in Social Networks Analysis and Mining
Twitinfo: aggregating and visualizing microblogs for event exploration
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Community detection in Social Media
Data Mining and Knowledge Discovery
Capturing Social Data Evolution Using Graph Clustering
IEEE Internet Computing
Hi-index | 0.00 |
In recent years, Online Social Networks (OSNs) have been widely adopted by people around the globe as a means of real-time communication and opinion expression. As a result, most real-world events and phenomena are actively discussed online through OSNs such as Twitter and Facebook. However, the scale and variety of such discussions often hampers their objective analysis, e.g. by focusing on specific messages and ignoring the overall picture of a phenomenon. To this end, this paper presents an analysis framework to assist the study of trends, events and interactions performed between online communities. The framework utilizes an adaptive dynamic community detection technique based on the Louvain method to study the evolution, overlap and cross-community dynamics in irregular, dynamically selected graph snapshots. We apply the proposed framework on a Twitter dataset collected by monitoring discussions around tweets containing extreme right political vocabulary, including messages around the Greek Golden Dawn party. The proposed analysis enables the extraction of new insights with respect to influential user accounts, topics of discussion and emerging trends, which could assist the work of journalists, social and political analysis scientists, but also highlights the limitations of existing analysis methods and poses new research questions.