@inproceedings{b3ef7865bd9a45c6be61f72b07b6fdf8,
title = "Compression-based Arabic text classification",
abstract = "Text classification (TC) is one of the fundamental problems in text mining. Plenty of works exist on TC with interesting approaches and excellent results; however, most of these works follow a word-based approach for feature extraction. In this work, we are interested in an alternative (byte-based or character-based) approach known as compression-based TC (CTC). CTC has been used for some languages such as English and Portuguese and it is shown to have certain advantages/ disadvantages compared with word-based approaches. This work applies CTC on the Arabic language with the purpose of investigating whether these advantages/disadvantages exists for the Arabic language as well. The results are encouraging as they show the viability of using CTC for Arabic TC.",
author = "Haneen Ta'amneh and Keshek, \{Ehsan Abu\} and Issa, \{Manar Bani\} and Mahmoud Al-Ayyoub and Yaser Jararweh",
note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 2014 11th IEEE/ACS International Conference on Computer Systems and Applications, AICCSA 2014 ; Conference date: 10-11-2014 Through 13-11-2014",
year = "2014",
doi = "10.1109/AICCSA.2014.7073253",
language = "English",
series = "Proceedings of IEEE/ACS International Conference on Computer Systems and Applications, AICCSA",
publisher = "IEEE Computer Society",
pages = "594--600",
booktitle = "2014 IEEE/ACS 11th International Conference on Computer Systems and Applications, AICCSA 2014",
address = "United States",
}