Semi-supervised fuzzy learning in text categorization

Semi-supervised learning has attracted a lot of attention in recent years. Different from traditional supervised learning. Semi-supervised learning makes use of both labeled and unlabeled samples. In text categorization, traditional classifier prefer lots of samples and each category have same number of simples, but collecting labeled examples costs human efforts and certain category may be can´t find abundance samples; this situation would lead to low classification accuracy. In this paper, we proposed a semi-supervised text classifier based on fuzzy c-means algorithm. Experiment show that our method has better performance in small samples and unbalance samples.