ABSTRACT
Artificial intelligence in education comes of age in systems now called “intelligent tutors,” a step beyond traditional computer-assisted instruction. Computer-assisted instruction evolves toward intelligent tutoring systems (ITSs) by passing three tests of intelligence. First, the subject matter, or domain, must be “known” to the computer system well enough for this embedded expert to draw inferences or solve problems in the domain. Second, the system must be able to deduce a learner’s approximation of that knowledge. Third, the tutorial strategy or pedagogy must be intelligent in that the “instructor in the box” can implement strategies to reduce the difference between expert and student performance. At the foundation of ITSs, therefore, one finds three special kinds of knowledge and problem-solving expertise programmed in a sophisticated instructional environment. This book examines these knowledge foundations—expert knowledge, student diagnostic knowledge, and the instructional or curricular knowledge—in detail. This book also describes (a) how these kinds of knowledge are embodied in computer-assisted instructional environments; (b) how these systems accrue the advantages of advanced computer interface technologies; (c) how ITSs will emerge in the real world of complex problem solving; and finally (d) how researchers must learn to evaluate the effectiveness and overall quality of these dynamic systems in a world where one day machine tutoring will be taken for granted.
