Study of a New Parallel K_NN Network Public Opinion Classification Algorithm Based on Hadoop Environment

Article Preview

Abstract:

A new kind of network public opinion classification method based on K_ nearest neighbor (K_NN) classification algorithm in Hadoop environment is studied in this paper. In the light of distributed storage and parallel processing Characteristics of Hadoop platform, the parallel K_NN classification algorithm in the frame of MapReduce is designed. The classification ability and execution efficiency of proposed scheme is verified and the results show that the parallel K_NN algorithm enhances the network public opinion classification precision and execution efficiently.

You might also be interested in these eBooks

Info:

Periodical:

Pages:

1624-1627

Citation:

Online since:

September 2014

Authors:

Export:

Price:

Permissions CCC:

Permissions PLS:

Сopyright:

© 2014 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

* - Corresponding Author

[1] X.P. Qin, H.J. Wang, X.Y. Du. Big Data Analysis—Competition and Symbiosis of RDBMS and MapReduce [J]. Journal of Software, 2012, 23(1)32-45.

DOI: 10.3724/sp.j.1001.2012.04091

Google Scholar

[2] C.C. You, G.G. Zhang. A Kind of Efficient Search Method Based on Big Data [J]. Computer Science, 2013, 40(6): 183-186.

Google Scholar

[3] J.L. Li, H.G. Fu. Improved KDE-based Data Classification Algorithm [J]. Control and Decision, 2010, 25(4): 507-515.

Google Scholar

[4] Ryunosuke Chiba, Mika Sato-Ilic. Analysis of Web Survey Data based on Similarity of Fuzzy Clusters[J]. Procedia Computer Science, 2012(12) 224-229.

DOI: 10.1016/j.procs.2012.09.060

Google Scholar

[5] Kaiquan Xu , Xitong Guo, Jiexun Li. Discovering target groups in social networking sites[J]. Electronic Commerce Research and Applications, 11(2012)318-334.

DOI: 10.1016/j.elerap.2012.01.002

Google Scholar