Answers are grounded in this paper and cite their sources.
In the era of internet-connected devices, the amount of unstructured data is multiplying in many different types of file formats. In particular, a great deal of knowledge is hidden in the vast amounts of textual data such as emails, blogs, tweets, and log files. The primary issue in this kind of textual data is to classify its content into predefined classes expeditiously in real time. Hence this research paper investigates the deployment of the state-of-the-art Machine Learning (ML) algorithms such as decision tree, k-nearest neighbourhood, Rocchio, ridge, passive-aggressive, multinomial naïve Bayes, Bernoulli naïve Bayes, support vector machine, artificial neural network including perceptron, stochastic gradient descent, back-propagation neural network in automatic classification of text documents on benchmark datasets such as 20Newsgroup, BBC news, BBC sports and IMDB. Finally, the performance of all the aforementioned built-in classifiers is compared and empirically evaluated using the well-defined metrics such as accuracy, error rate, precision, recall, f-measure and Kappa statistics.
No takes yet. Share an insight, caveat, or question.
Bichitrananda Behera (2019) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: