Knowledge discovery with genetic programming for providing feedback to courseware author. User Modeling and User-Adapted Interaction: The

Abstract. This paper describes how to use evolutionary algorithms as data mining methods for discovering prediction rules in databases. These rules will be used to improve courseware, especially Adaptive Systems for Web-based Education (ASWE). Our aim is to discover important dependence relationships among the usage data picked up during students ’ sessions. This knowledge may be very useful for the teacher or the author of the course, who could decide what modifications will be the most appropriate to improve the effectiveness of the course. In order to perform the discovery of rules we have used Grammar-Based Genetic Programming (GBGP) with multi-objective optimization techniques. Using that, we can interactively specify the form of the rules and we can choose several evaluation measures of the rules ’ quality at the same time. Finally, we have developed a specific mining tool for discovering rules which facilitates the usage of the proposed discovering and improving ASWE methodology.