Title :
Research on the text clustering algorithm based on latent semantic analysis and optimization
Author :
Chun-hong, Wang ; Li-Li, Nan ; Yao-Peng, Ren
Author_Institution :
Comput. Sci. & Technol., Yun cheng Univ., Yun cheng, China
Abstract :
The text clustering based on Vector Space Model has problems, such as high-dimensional and sparse, unable to solve synonym and polyseme etc. And meanwhile, k-means clustering algorithm has shortcomings, which depends on the initial clustering center and needs to fix the number of clusters in advance. Aiming at these problems, in this paper, a text clustering algorithm based on Latent Semantic Analysis and Optimization is proposed. This algorithm can not only overcome the problems of Vector Space Model, but also can avoid the shortcomings of k-means algorithm. And compared with the text clustering algorithm based on Latent Semantic Analysis and the text clustering algorithm based on Vector Space Model and optimization, our algorithm is proved which can preferably improve the effect of text clustering, and upgrade the precision ratio and recall ration of text.
Keywords :
optimisation; pattern clustering; text analysis; vectors; global optimization algorithm; k-means clustering algorithm; latent semantic analysis; text clustering algorithm; vector space model; Latent Semantic Analysis; Vector Space Model; clustering optimization; k-means clustering algorithm; text clustering;
Conference_Titel :
Computer Science and Automation Engineering (CSAE), 2011 IEEE International Conference on
Conference_Location :
Shanghai
Print_ISBN :
978-1-4244-8727-1
DOI :
10.1109/CSAE.2011.5952891