A Case-Based Approach for Building Intelligent Tutoring Systems

Intelligent tutoring systems (ITS) provide the benefits of one-on-one instruction in an automatic way and cost effectively, keeping in mind their multidisciplinary nature. The development of an ITS is often criticized for being a complex and challenging process as individual students' needs change and often they do not realize that they need help. Consequently, such a system must be capable of dynamically adapting and monitoring each student, developing a model of their knowledge, skills and expertise. Based on the learner student model, an ITS must present instructional strategies in terms of both the content and the style, and provides explanations and practice problems as needed. The advances in the development of the computer technologies has facilitated the use and design of ITS. Nevertheless, ITS research progress has been impeded by the lack of modular system architectures, reusable components and sharable knowledge bases. Each new research or development effort typically starts from scratch, without a foundation on which to build. In this paper some of the actual limiting problems of the ITS are studied. The main contribution of this work is resumed in a proposed framework. The framework incorporates a knowledge base where data and knowledge related to the problem are maintained and a model related to the student, teaching and environmental issues together with pedagogical perspectives. We consider in the ITS context the agents' technology for address issues of modularity and reusability; and Case-Based Reasoning to store students' interactions and feedback with the ITS, in order to maintain past memory experiences and then derive new paths for teaching.