retrieval of information required.
There are many areas for subjects such not medicine, sports, health, law, etc., although not process not classification texts we facilitate search and tell us where should be to search, so do not waste time in retrieving information I have no relation of the request.
The text classification is the automated technique used to classify the text in predefined category which is more related to the text.
in this day the manual classification become very difficult with the huge data that's uploaded daily on the internet and it's need long time, in other words we can say it's impossible work in the internet world, so the automated text classification technique make the classify Process very simple and faster.
Most research has focused on classification texts written in the English Language more than the Arabic language because of the Arabic nature and the difficulty of their structures the difficult nature in the Arabic language make it more complex and difficult to deal with them because of the many rules and anomalous characteristics, but it has become necessary to deal with this language because of the wide spread over the Internet.
To facilitate the search and retrieval in the Arabic language there are many algorithms working on the text classification that helps to retrieve data related to research in a short time and more accurate
In this thesis we have studied many classification algorithms of Arabic-language texts.
There are many algorithms used for classification, but any of them better?.
so we chose some of the text and classification algorithms and we have applied it's to the dataset written in Arabic language, each of these algorithms have the characteristics and standards, such as precision, Recall, F-measure and accuracy.
the our problem in this work is to find when the algorithm is the best of other depend on the result which collected from WEKA software and make comparisons between classifier algorithms .
In these days have become Arabic texts spread largely due to the spread of the Internet and the ease of access and upload Arabic files dramatically, this led to the difficulty of research and an increase in the time to reach the required results.
This is what makes researchers and programmers are looking for solutions to these developments to facilitate the search and retrieval operations.
The huge increase in the number of Arabic texts on the Internet has increased the complexity, so the process of classifying texts working to improve the process of retrieving data, the researchers and programmers developed algorithms for the classification of Arabic-language texts, and there are many of them, and each of these algorithms have characteristics that distinguish them from other, such as the accuracy and precision and recall differ these characteristics depending on the nature of the data.
in this thesis we applied some algorithms on a different of Arabic dataset and make comparison between them...