Abstract—This paper proposes the idea of applying a
clustering ensemble based genetic algorithm in the area of
complex social network mining. The algorithm introduces
clustering ensemble into the crossover operator and employs
the clustering information of the parents to generate new
individuals, which avoids the problems that caused by simply
exchanging string between crossover operators without
consider the contents. In population generation, Markov
random walk strategy is employed to maintain the diversity of
the individuals as well as the clustering accuracy. The
algorithm also uses a local searching mechanism in crossover
operators to reduce the searching space and improve the speed
of convergence. Comparing with existing mining algorithms in
social network, the proposed algorithm is more effective
proved by experiments in both simulation and real world social
networks.
Index Terms—Community structure, complex network,
genetic algorithm, clustering ensemble, data mining.
The authors are with the College of computer and software, Shenzhen
University, Shenzhen 518060, Guangdong, China (e-mail:
lunan@szu.edu.cn, 690485801@qq.com, qinlei626@gmail.com).
[PDF]
Cite:Nan Lu, Yuanyuan Jin, and Lei Qin, "Network Community Structure Clustering Algorithm Based on the Genetic Theory," Journal of Advances in Computer Networks vol. 1, no. 2, pp. 88-93, 2013.
