Urdu News Content Classification Using Machine Learning Algorithms

Abstract

As the world has become a global village, the flow of news in terms of volume and speed increases. It is necessary to engage computing machines for assisting people in dealing with this massive data. The availability of different types of news and such material on the Internet serves as a source of information for billions of users. Millions of people in our subcontinent speak and understand Urdu. There are several classification techniques that are available and are applied to classify English news like political, Education, Medical, etc. Plenty of research work has been done in multiple languages but Urdu is still to be worked on due to a lack of resources. This research evaluates the performance of twelve (12) different Machine learning classifiers for the Urdu News text Classification problem. The analysis was performed on a relatively big and recent collection of Urdu text that contains over 0.15 million (153,050) labeled instances of eight different classes. In addition, after applying pre-processing techniques, the TF-IDF weighting technique was adopted for feature selection and data extraction. After evaluating various machine learning methods, the SVM outperforms the other eleven algorithms with an accuracy of 91.37 %. We also compare its results with other classifiers like linear SVM, Logistic regression, SGD, Naïve bays, ridge regression, and a few others.