Increasing Accuracy of K-Nearest Neighbor Classifier for Text Classification

k - Nearest Neighbor Rule is a well-known technique for text classification. The reason behind this is its simplicity, effectiveness, easily modifiable. In this paper, we briefly discuss text classification, k-NN algorithm and analyse the sensitivity problem of k value. To overcome this problem, we introduced inverse cosine distance weighted voting function for text classification. Therefore, Accuracy of text classification is increased even if any large value for k is chosen, as compared to simple k Nearest Neighbor classifier. The proposed weighted function is proved as more effective when any application has large text dataset with some dominating categories, using experimental results.