Research on Internet Public Opinion Hotspot Detection Based on Document Cluster

Gensheng Wang

Electronic Business department Jiangxi University of Finance and Economics Nanchang, China

Abstract: In order to strengthen management and monitor to Internet, collection and analysis of public opinion information is a realistic problem solved urgently for the present government departments. The paper present a new algorithm for detecting internet public opinion hotspot based on K_means and particle swarm optimization algorithm. First, the limitations of the K_means and particle swarm optimization algorithm are analyzed. Second, the algorithms of K_means and particle swarm optimization algorithm are integrated and corresponding improvements including algorithm principle, the exploration ability of global solution , algorithm calculation process are presented to overcome the limitations of original algorithms. Finally, the experimental results verify that the new algorithm can improve effectiveness and validity of hotspot discovery of internet public opinions when used for internet public opinion hotspot detection practically.

Keywords: Internet public opinion hotspot detection; Document cluster; K_means; Particle swarm optimization