Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Agglomerative clustering enhanced GA for optimal seed selection in online social networks

Agglomerative clustering enhanced GA for optimal seed selection in online social networks The social media revolution has brought tremendous change in business strategies for marketing and promoting the products and services. Online social networks have become prime choice to promote the products because of the large size of online communities. Identification of seed nodes or identifying the users who are able to maximize the spread of information over the network is the key challenge faced by organizations. It is proved as non-deterministic polynomial-time hard problem. The purpose of this paper is to design an efficient algorithm for optimal seed selection to cover the online social network as much as possible to maximize the influence. In this approach, agglomerative clustering is used to generate the initial population of seed nodes for GA.Design/methodology/approachIn this paper agglomerative clustering based approach is proposed to generate the initial population of seed nodes for GA. This approach helps in creating the initial populations of Genetic algorithm from different parts of the network. Genetic algorithm evolves this population and aids in generating the best seed nodes in the network.FindingsThe performance of of proposed approach is assessed with respect to existing seed selection approaches like k-medoid, k-means, general greedy, random, discounted degree and high degree. The algorithms are compared over networks data sets with varying out-degree ratio. Experiments reveal that the proposed approach is able to improve the spread of influence by 35% as compared to contemporary techniques.Originality/valueThis paper is original contribution. The agglomerative clustering-based GA for optimal seed selection is developed to improve the spread of influence in online social networks. This paper is of immense importance for viral marketing and the organizations willing to promote product or services online via influential personalities. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png International Journal of Web Information Systems Emerald Publishing

Agglomerative clustering enhanced GA for optimal seed selection in online social networks

International Journal of Web Information Systems , Volume 18 (5/6): 14 – Dec 12, 2022

Loading next page...
 
/lp/emerald-publishing/agglomerative-clustering-enhanced-ga-for-optimal-seed-selection-in-GXl4K5TE9w

References (23)

Publisher
Emerald Publishing
Copyright
© Emerald Publishing Limited
ISSN
1744-0084
eISSN
1744-0084
DOI
10.1108/ijwis-02-2022-0042
Publisher site
See Article on Publisher Site

Abstract

The social media revolution has brought tremendous change in business strategies for marketing and promoting the products and services. Online social networks have become prime choice to promote the products because of the large size of online communities. Identification of seed nodes or identifying the users who are able to maximize the spread of information over the network is the key challenge faced by organizations. It is proved as non-deterministic polynomial-time hard problem. The purpose of this paper is to design an efficient algorithm for optimal seed selection to cover the online social network as much as possible to maximize the influence. In this approach, agglomerative clustering is used to generate the initial population of seed nodes for GA.Design/methodology/approachIn this paper agglomerative clustering based approach is proposed to generate the initial population of seed nodes for GA. This approach helps in creating the initial populations of Genetic algorithm from different parts of the network. Genetic algorithm evolves this population and aids in generating the best seed nodes in the network.FindingsThe performance of of proposed approach is assessed with respect to existing seed selection approaches like k-medoid, k-means, general greedy, random, discounted degree and high degree. The algorithms are compared over networks data sets with varying out-degree ratio. Experiments reveal that the proposed approach is able to improve the spread of influence by 35% as compared to contemporary techniques.Originality/valueThis paper is original contribution. The agglomerative clustering-based GA for optimal seed selection is developed to improve the spread of influence in online social networks. This paper is of immense importance for viral marketing and the organizations willing to promote product or services online via influential personalities.

Journal

International Journal of Web Information SystemsEmerald Publishing

Published: Dec 12, 2022

Keywords: Genetic algorithm; Information diffusion; Agglomerative clustering; Influence maximization; Seed selection

There are no references for this article.