Examinations on the Performance of Classification Models for Thai News Articles








Abstract

This research aims to examine automatic models to classify Thai online news articles. The data set is six thousands of news articles from three mainstream websites. The news articles are classified into four categories-crime news, politic news, sport news, and entertainment news. Examinations on the classification algorithms of Decision Tree, Support Vector Machine (SVM), and Deep Learning are conducted. The performance is measured by the accuracy, the recall, the precision, and the F-Measure. The results show that the accuracies of Decision Tree, SVM, and Deep Learning models are 86%, 94%, and 95%, respectively.


Modules


Algorithms

Machine learning algorithms


Software And Hardware

• Hardware: Processor: i3 ,i5 RAM: 4GB Hard disk: 16 GB • Software: operating System : Windws2000/XP/7/8/10 Anaconda,jupyter,spyder,flask Frontend :-python Backend:- MYSQL