Evaluation of Different Query Expansion Techniques by using Different Similarity Measures in Arabic Documents

Millions of users search daily for their needs using internet and other information stores, they search by writing their queries. Unfortunately, these queries may fail to reach to their needs, this fail known as word mismatch. One way of handling this Word mismatch is by using a thesaurus, that shows (usually semantic) the relationships between terms. The main goal of this study is to design and build an automatic Arabic thesaurus using Local Context Analysis technique 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. This technique can be used in any special field or domain to improve the expansion process and to get more relevant documents for the user's query. Results of this study were compared with the classical information retrieval system. Two hundred and forty two Arabic documents and 59 Arabic queries were used for building the requirements of the thesaurus, such as inverted File, indexing, term-term cooccurrence matrix, etc. All of these documents involve computer science and information system vocabulary. The system was implemented in ORACLE 11 g environment and run on Pentium-4 laptop with 2.13GHz speed, 2.86MB RAM memory, and hard disk capacity of 500GB. The study has shown that the Local Context Analysis technique improved the retrieval in a remarkable way better than the classical retrieval method.