Designing and Building an Automatic Information Retrieval System for Handling the Arabic Data

Abstract

This paper aimed to design and build an Automatic Information Retrieval System to handle the Arabic data. Also, this paper presents some type of comparison between the retrieval results using the vector space model in two different indexing methods: the full-ward indexing and the root indexing. The proposed Automatic Information Retrieval system was implemented and built using a traditional model technique: Vector Space Model (VSM) where the cosine measure similarity was used. The output results indicate and show that the root indexing improved the retrieval performance more than the full-ward indexing on the Arabic documents; furthermore it reduces the size of stored data and minimizes the time of system processing.