New method of hybrid intelligent text clustering based on semantic similarity
一种基于语义相似度的群智能文本聚类的新方法*

The problem with the text clustering algorithm based on vector space model (VSM) is that semantic information between words and the link between the various dimensions are overlooked, resulting in inaccuracy in the text similarity calculation, this paper proposed a hybrid intelligent algorithm based on computing the text semantic similarity. This algorithm combined the good global search capability of simulated annealing algorithm and the good positive feedback ability of ant colony algorithm. It extended the algorithm to analyze the text according to its semantic, then used K-means clustering to seed the initial solution and the ant colony algorithm and simulated annealing algorithm to adjust the initial cluster. Through the result, this algorithm can improve the clustering precision and recall rate and the efficiency of the hybrid algorithm is verified.