A New Text Categorization (TC) Algorithm for Classifying Arabic Language Text Document

摘要

Automatic text categorization (TC) has become one of the most interesting fields for researchers in data mining, information retrieval, web text mining, as well as natural language processing paradigms due to the vast number of new documents being retrieved for various information retrieval systems. This paper proposes a new TC technique, which classifies Arabic language text documents using clustering algorithm. The proposed technique is based on classifying documents using the Local Sparsity Coefficient-mine algorithm (LSC-mine algorithm); this algorithm is an outlier detection algorithm that belongs to clustering paradigm. The adopted algorithm is capable of detecting outlier points in a spatial space; the discovering process is accomplished through computing the Local sparsity ratio (LSC), which indicates the outlier-ness of a certain point. The algorithm is conducted and experemints on Arabic document files gathered from the internet website. The algorithm is implemented using the Visual C++.NET programming language.