EFFECTIVE INFORMATION RETRIEVAL METHOD BASED ON MATCHING ADAPTIVE GENETIC ALGORITHM

Information Retrieval (IR) System is very complex in nature due to the complex interactions between documents and queries, which means that the matching of document representations and query representations is not straightforward. The Genetic Algorithm (GA) is widely used in IR systems to improve the effectiveness such systems. This study uses the Vector Space Model (VSM) and the Extended Boolean Model (EBM) to compute the similarities between queries and documents. Two fitness functions are proposed in this paper: One as fitness function and the other as adaptive mutation. Then comparing each of these functions with a number of ratio mutations that have been introduced to get better results. The experimental results reveal that the proposed cosine function outperformed other fitness models.