Shandong Institute of Business and Technology, Yantai ,China

---

Abstract—Text clustering is one of the key research areas in data mining. k-medoids algorithm is a classical division algorithm, and can solve the problem of isolated points, But it often converges to local optimum. This article presents a improved social evolutionary programming(K-medoids Social Evolutionary Programming,KSEP). The algorithm is the k-medoids algorithm as the main cognitive reasoning algorithm. and Improved to learning of Paradigm、Optimal paradigm strengthening and attenuation and Cognitive agent betrayal of paradigm. This algorithm will increase the diversity of species group and enhance the optimization capability of social evolutionary programming, thus improve the accuracy of clustering and the capacity of acquiring isolated points.

Index Terms—Text clustering, K-medoids algorithm, social evolutionary programmi ng

[PDF]

Cite: ZhanGang Hao, "A New Text Clustering Method Based on KSEP," Journal of Software vol. 7, no. 6, pp. 1421-1425, 2012.