Year: 2013
Type: preprint
Abstract: To analyze the activities in an Online Social network (OSN), we introduce the concept of "Node of Attraction" (NoA) which represents the most active node in a network community. This NoA is identified as the origin/initiator of a post/communication which attracted other nodes and formed a cluster at any point in time. In this research, a genetic algorithm (GA) is used as a data mining method where the main objective is to determine clusters of network communities in a given OSN dataset. This approach is efficient in handling different type of discussion topics in our studied OSN - comments, emails, chat expressions, etc. and can form clusters according to one or more topics. We believe that this work can be useful in finding the source for spread of this GA-based clustering of online interactions and reports some results of experiments with real-world data and demonstrates the performance of proposed approach.
Source: arXiv (Cornell University)
Language: English
Subfield: Statistical and Nonlinear Physics
Field: Physics and Astronomy
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W1490002237