Building an Automatic Thesaurus to Enhance Information Retrieval

One of the major problems of modern Information Retrieval (IR) systems is the vocabulary Problem that concerns with the discrepancies between terms used for describing documents and the terms used by the researcher to describe their information need. We have implemented an automatic thesurs, the system was built using Vector Space Model (VSM). In this model, we used Cosine measure similarity. In this paper we use selected 242 Arabic abstract documents. All these abstracts involve computer science and information system. The main goal of this paper is to design and build automatic Arabic thesauri using term-term similarity that can be used in any special field or domain to improve the expansion process and to get more relevance documents for the user's query. The study concluded that the similarl thesaurus improved the recall and precision more than traditional information retrieval system in terms of recall and precision level.