A text clustering algorithm based on find of density peaks

The text clustering is one of core issues in the field of text mining and information retrieval. The clustering algorithm is divided into four categories: the partitioned clustering algorithm, the hierarchical clustering algorithm, density-based clustering algorithm, as well as intelligence clustering algorithm, but at present, many of which cannot meet the demand of speed and self-adapting about text clustering. Therefore this paper proposed a text clustering algorithm based on find of density peaks. The algorithm was implemented by the calculation of text distance and density, which was in accordance with calculation of the text vector similarity. SVM was used to express text to obtain the vector mapping for the similarity calculation. The next work was the finding of the local density and the distance from points of higher density of each text, removing the noise points, selecting the cluster center. The remaining points were assigned into the cluster which its nearest cluster center represented. According to several sets of contrast experiment, the density-based text clustering has an advantage of reliability and robustness.