An approach to an adaptive information retrieval agent using genetic algorithms with fuzzy set genes

We present the genetic information retrieval agent filter (GIRAF) as an approach to adaptive Internet information retrieval using genetic algorithms (GAs) with fuzzy set genes. Each gene characterizes documents by a keyword and an associated occurrence frequency represented by a certain type of a fuzzy subset of the set of positive integers. For the representation of the user's information needs, we maintain a population of chromosomes, each consisting of a fixed number of genes. Each chromosome is associated with a fitness which may be considered the system's believe in the hypothesis that the chromosome, as a query, represents the user's information needs. Based on the user's evaluation of the retrieved documents by the chromosome, compared the scores computed by the system, the fitness of the chromosomes is adjusted. We present and discuss results from testing a prototype of GIRAF in retrieving documents from the Internet.