An Improved Growing LVQ for Text Classification

KNN as a simple classification method has been widely applied in text classification. There are two problems in KNN-based text classification: the large computation load and the deterioration of classification accuracy caused by the uneven distribution of training samples. To solve these problems, we propose a new growing LVQ method and apply it to text classification based on minimizing the increment of learning errors. Our method can generate a representative sample (reference sample) set after one phase of training of sample set, and hence has a strong learning ability. The experiment shows the improvement on both time and accuracy. For our algorithm, we also proposed a learning sequence arrangement method which performs better than others.