Terrell N. Chandler & Janet L. Kolodner
The Science Education Advisor (SCIED) is a case-based hypermedia browsing tool designed to collect and dispenses ideas and advice for the teaching of science in elementary school. Our approach has been to apply what the researchers in the cognitive and educational communities have learned about cognitive functioning to build a system which augments the memories of teachers, advises teachers on how to best apply a activity or pedagogical approach to their class, and, promotes communication and collaboration within and across the educational and scientific community. Based on the teachers stated interests SCIED suggests candidate activities for the teacher to adopt. It also identifies problems and gives solutions for instruction in content areas (e.g. issues involved in the teaching of chemistry), in the teaching of science process skills (e.g. getting kids to make inferences from their observations) and in promoting a positive learning environment (e.g. how to group kids for cooperative learning). In addition to providing activities and abstract solutions to teachers' problems, SCIED provides teachers with advice through concrete guidelines and "war" stories from teachers who have used the activity before.
Two years ago, we proposed the use of case-based decision aiding (Kolodner, 1991) as a methodology for creating a system to advise teachers. Case-based decision aiding is based on the case-based reasoning paradigm. A case-based system augments the memory of a person by making the experiences of others available. In 1991, our system, then called AI-ED, was in its infant stages. While we knew that case-based reasoning provided a good base for building such a system, there were many issues that we knew we still needed to address, including the content of the case library, the representation of cases, the indexing of cases, and the creation of an interface that would be easy to use. Since that time, we have interviewed 40 experienced and inexperienced teachers who teach a diverse cross section of the Atlanta elementary and middle school population to collect these teachers' experiences and to find out what is hard for them and what they need help with. This analysis has allowed us to begin to address the issues brought up in the earlier paper. In this paper, we report our current solutions along each of these dimensions and present SCIED, our current implementation.Presented at the World Conference on Artifical Intelligence in Education, August 1993. Edinburgh, Scotland