the Computer Science Department at the University of Technology grants a master's degree to the student Hala Diaa for her dessertation "Intelligent system for document classification based on content"
The researcher present a proposal to classify documents into the correct category based on their content, called the Intelligent Document Classification System (IDC). The IDC system uses four types of pre-processing: Tokenization to separate a word from others, Normalization to delete all non-words, Remove stop words to delete all non-important words, and porter algorithm to get the root of the word. The Bow model is used to extract features from documents and use the weighting method to assign weight to each feature.
The discussion committee was chaired by Assc.Prof. Dr.Rehab Falih Hassan and Assc. Prof.Dr. Esraa Abdel-Amir and Assc. Prof.Dr. Haitham Abdul Latif as members from Al-Salam University and Assc. Prof.Dr. Hassanein Samir.