Supervised Machine Learning Text Classification: A Review

Most of the data available today are in the form of text. This text data can be very useful and this is the point where text mining comes into the picture. Proper text mining can convert unstructured text data into useful data resources. This paper has tried to provide an overview of text classification with references to supervised learning classifiers. Various datasets, text preprocessing, algorithms, and evaluation techniques used in text classification with emphasis on Naïve Bayes, support vector machine, decision trees, K-nearest neighbor algorithms, and their advantages and disadvantages have been briefly discussed in this paper.