Approach for Text Classification Based on the Similarity Measurement between Normal Cloud Models

Table 1

Datasets and their characteristics.

Datasets	Degree of similarity between categories	Number of articles	Dimensionality of categories
Featured Articles (Wikipedia)	Normal	1159	23
Vehicles (Wikipedia)	Low	640	4
Mathematics (Arxiv.org)	High	320	8
20-Newsgroups (CMU Text Learning Group)	Normal	20,000	20