@article{94,
  author = {Fouzi Harrag, Eyas Al-Qawasmah, Aboubekeur Hamdi-Cherif},
  title = {Performance of Decision Trees on Arabic Text Categorization},
  journal = {Journal of Digital Information Management},
  year = {2009},
  volume = {7},
  number = {6},
  doi = {},
  url = {http://www.dline.info/fpaper/jdim/v7i6/8.pdf},
  abstract = {Text classifi cation is the task of assigning a document to one or more of pre-defi ned categories based on its contents. This paper presents the results of classifying Arabic text documents using a decision tree algorithm. Experiments are performed over two self collected data corpus and the results show that the suggested hybrid approach of Document Frequency Thresholding using an embedded information gain criterion of the decision tree algorithm is the preferable feature selection criterion. The average accuracy of using Feature selection is 0.93 for the scientifi c corpus, while for the literary corpus the average accuracy is 0.91. We also conclude that the effectiveness of the decision tree classifi er was increased as we increase the training size.},
}