News Classification: A Data Mining Approach

Objectives: Text classification is one of the important applications of data mining. Text classification classifies text documents on the basis of words, phrases, combination of words etc. into predefined class labels. Method/Analysis: Present study classifies news data into four predefined classes namely Business, Entertainment, sports and Technology. For text classification WEKA an open source data mining tool is used. Different classification algorithms are applied on News data set. A comparative study of these algorithms is done based on Accuracy, Time, Errors and ROC to predict the best algorithm for news data set classification. Findings: Present study analyzed result on the basis of accuracy, time, error and ROC curve. Present work concludes that NaïveBayes Multinomial algorithm is best for news classification.