An immune based algorithm for Chinese network short text clustering

Network short text clustering is a major technology in network content security. Since Chinese network short text is less of keywords and full of anomalous writings, the traditional text clustering method is not directly suitable for network short text clustering. This paper presents an immune network regulation based method to cluster Chinese network short texts. First, Chinese N-gram chunks are extracted and transformed to Chinese pinyin to form the feature representation to each Chinese network short text, so as to relieve these two characteristics' bad influence on the clustering performance. Then, the network short text set is constructed as a dynamic network and an immune network learning mechanism is used to learn the similarity among short texts and therefore to gain a better clustering result. Experiments show our method can get better performance in Chinese network short text clustering, compared with traditional method such as K-means.