Information filtering using fuzzy-genetic algorithm approach

Automatic filtering of information has become increasingly important in recent years due to large availability of electronic information. We present an approach for optimization of Information Retrieval System (IRS) by genetic algorithm and fuzzy sets in an adaptive filtering process. From the observed user preferences regarding documents in the sets retrieved, the system learns from the user's information needs. An interest profile is created that represents the needs as learned from the observed preferences in the user's area of interest. The proposed system will act as an offline information-filtering agent. The documents have been already downloaded from the Internet using google. The system generates a recommendation based on adaptive filtering using a set of keywords extracted from all documents evaluated by user. The process starts with the initial set of documents retrieved as the answer to user's initial query in the area of interest. The preferences given by the user are learned through explicit feedback on retrieved documents. The agent filters and ranks the retrieved information according to user's preferences using Genetic Algorithm (GA) and Fuzzy Set Theory. The system has been implemented using Java on Windows 98.