How to cite this WIREs title:
WIREs Data Mining Knowl Discov
WIREs Data Mining Knowl Discov
Impact Factor: 4.476
A novel social network mining approach for customer segmentation and viral marketing
Focus Article
Published Online: Jul 13 2016
DOI: 10.1002/widm.1183
Can't access this content? Tell your librarian.
Emergence of social networks facilitates individuals to communicate, share opinions and form communities. Organizations benefit from social networks in monitoring customers’ behavior. Social networks mining and analysis aims to segment customers and determine the most influential actors for viral marketing. In this article, we propose a novel social network mining approach for influential analysis and community detection. The community detection task benefits from the most influential users in the network. The proposed approach identifies the most influential users by using a direct mining leaders discovery algorithm and uses these leaders as core points to expand communities around them. This is based on the observation that communities tend to be formed around users of great influence. Extensive experiments have been completed on a real dataset and results show that our approach can contribute in identifying communities of high quality. WIREs Data Mining Knowl Discov 2016, 6:177–189. doi: 10.1002/widm.1183 This article is categorized under: Fundamental Concepts of Data and Knowledge > Motivation and Emergence of Data Mining Technologies > Structure Discovery and Clustering
Average separability for our proposed algorithm over both similarity measures (weight = common neighbors and common actions).
[
Normal View
|
Magnified View
]
Average conductance for our proposed algorithm over both similarity measures (weight = common neighbors and common actions).
[
Normal View
|
Magnified View
]
Average separability for our proposed algorithm versus the hierarchical diffusion algorithm (weight = common actions).
[
Normal View
|
Magnified View
]
Average conductance for our proposed algorithm versus the hierarchical diffusion algorithm (weight = common actions).
[
Normal View
|
Magnified View
]
Average separability for our proposed algorithm versus the hierarchical diffusion algorithm (weight = common neighbors).
[
Normal View
|
Magnified View
]
Average conductance for our proposed algorithm versus the hierarchical diffusion algorithm (weight = common neighbors).
[
Normal View
|
Magnified View
]