Optimizing information retrieval using evolutionary algorithms and fuzzy inference system

Abstract

With the rapid growth of the amount of data available in electronic libraries, through Internet and enterprise network mediums, advanced methods of search and information retrieval are in demand. Information retrieval systems, designed for storing, maintaining and searching large-scale sets of unstructured documents, are the subject of intensive investigation. An information retrieval system, a sophisticated application managing underlying documentary databases, is at the core of every search engine, including Internet search services. There is a clear demand for fine-tuning the performance of information retrieval systems. One step in optimizing the information retrieval experience is the deployment of Genetic Algorithms, a widely used subclass of Evolutionary Algorithms that have proved to be a successful optimization tool in many areas. In this paper, we revise and extend genetic approaches to information retrieval leverage via the optimization of search queries. As the next trend in improving search effectiveness and user-friendliness, system interaction will use fuzzy concepts in information retrieval systems. Deployment of fuzzy technology allows stating flexible, smooth and vague search criteria and retrieving a rich set of relevance ranked documents aiming to supply the inquirer with more satisfactory answers. © 2009 Springer-Verlag Berlin Heidelberg.