ATS - Adaptive Teaching System
by Marcus Specht
Web-based educational systems are becoming more and more popular and are used by a heterogenous user group. Users of educational Web-based systems differ in their goals, professional background, interests and knowledge of the subject matter. To optimize the efficiency and effectiveness of the learning process educational systems should adapt to this user features.
ATS is a Web-based educational system that mainly uses adaptation to the knowledge and the interests of learners to generate individualized hypermedia instruction. The system is based on a domain model of the subject matter, a didactical model how to teach a curriculum and learner modelling on different levels, eg preferences, interests, knowledge.
The domain model contains the knowledge about the subject matter. The knowledge base is represented as a conceptual network with different types of units and relations between them. Several types of information are associated with each unit. These are different kinds of text (introduction, several stages of teachtexts, summary), examples, demonstrations, playgrounds, and tests. In addition, each unit has prerequisites (units that the student should be familiar with before working on the unit) and consequences (possible outcomes and effects on other units). The tests, prerequisites and consequences are weighted according to their importance for a unit.
The didactical model represents the teacher's knowledge of how to teach units. It consists of two main parts: teaching strategies and diagnostic knowledge. The system has a default strategy for each concept type and teachers can specify a preferred strategy for a concept if needed. The diagnostic component stores the knowledge about several types of tests and how they have to be generated and evaluated.
In the learner model is stored the information about the material that a learner has used and how successful he/she worked on the material (eg, if tests are solved correctly, if the playground estimations were good or to what extend teachtexts where requested). Every action of a student has consequences for updating the learner model depending on the involved learning material and the previous experiences of a learner.
Based on these three components individualized web-content (html, vrml, pictures) can be generated and presented to a learner. Both, knowledge and interests are diagnosed at the beginning of the learning process with ATS and updated through the learning process to keep track of the changing needs. Taking into account the interest and the knowledge of a learner the system can adapt the instructional process on several levels:
- adapting the curriculum by selection of content
- adapting the presentation of contents by choosing appropriate media and combining them (adaptive multimedia presentation)
- adapting the teaching strategies for specific contents
- annotating hyperlinks
- recommending hyperlinks and contents.
Some adaptive methods used in ATS have been empirically evaluated and showed improvements in efficieny and effectiveness of learning compared to classical static hypermedia learning environments. Based on this results further research has to be done on complex interactions between adaptive methods and the dependencies between different user features and the effectiveness of adaptive methods for educational purposes. Beside that further developments will try to integrate social learning processes and goal based adaptation methods in ATS. An authoring tool for ATS could be easily integrated in the domain independent ATS framework and would allow new ATS systems to be build by teachers without any html or programming experience.
Marcus Specht - GMD
Tel: +49 22 41 14 2847
E-mail: Marcus Specht@gmd.de