Abstract
Aiming at the problems of low precision and instability in the current overlapping community partition results, a node label overlapping community partition algorithm based on entropy transformation (ECDA) is proposed. Firstly, a new initialization method is used to initialize the node label, which reduces the label waste caused by conventional algorithms. Secondly, combined with the certain similarity between direct friends and indirect friends in social networks, a new node similarity calculation method is defined. Using the similarity, the cumulative sum of node label weight and label weight is defined to obtain the membership degree as entropy. During label propagation, the node label and label weight are carried for asynchronous update, and the operation is repeated continuously until the node label set in the network no longer changes. Finally, the simulation results show that ECDA has a great improvement in the accuracy and stability of overlapping community division.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
