Beyond intelligent tutoring systems: Situations, interactions, processes and affordances

The idea of an intelligent system to support learning has been epitomised by that of an intelligent tutoring system (ITS). However, ITSs are, in fact, just a particular kind of intelligent system to support learning whose components reflect the values of the particular view that ITSs emphasise in regard to the nature of knowledge, learning and teaching, which have led to an architecture that focuses on representing the knowledge to be learned (domain model), inferring the learner's knowledge (learner model), and planning instructional steps to the learner (teaching model). On the other hand, other views of learning may lead to different needs in terms of knowledge representation, reasoning, and decision making capabilities in the intelligent systems that support them. Constructivist views, for example, emphasise different values and may require an entirely different architecture of intelligent system to support its philosophy of learning. This paper presents an architecture of an intelligent system to support learning that is able to address the issues that arise from constructivist theories of learning in a way that, rather than opposing to the standard ITS architecture, characterises a broader view in all its components which can be appropriately attuned to address the issues of particular philosophies.