@article{542,
  author = {M. Abbas, K. Smaili, D. Berkani},
  title = {Evaluation of Topic Identifi cation Methods on Arabic Corpora},
  journal = {Journal of Digital Information Management},
  year = {2011},
  volume = {9},
  number = {5},
  doi = {},
  url = {http://dline.info/fpaper/jdim/v9i5/1.pdf},
  abstract = {Topic Identifi cation is one of the important keys for the success of many applications. Indeed, there are few works in this fi eld concerning Arabic language because of lack of standard corpora. In this study, we will provide directly comparable results of six text categorization methods on a new Arabic corpus Alwatan-2004. Hence, Topic Unigram Language Model (TULM), Term Frequency/Inverse Document Frequency (TFIDF), Neural Network, SVM, M-SVM and TR have been experimented, and showed that TR-Classifi er is the most effi cient among the set of classifi ers, nevertheless, only binary SVM outperformed it thanks to its characteristics. Moreover, we should note that the size of Alwatan-2004 corpus used to achieve our experiments is considered the most important compared to any other Arabic corpus which had been used for topic identifi cation experiments until now. In addition, we aim through using small sizes of vocabularies to reduce the time of computation. This is important for adaptive language modeling, particularly Topic Adaptation, which is required in real time applications such as speech recognition and machine translation systems. Our experiments indicate that the results are better than other works dealing with Arabic text categorization.},
}