Four Faces of HAL: A Framework for Using Artificial Intelligence Techniques in Computer-Assisted Instruction

A conceptual framework for applying artificial intelligence (AI) techniques in computer-assisted instruction (CAI) is described. The student progresses through four phases (``faces´´) of interaction with the computer acting as ``benevolent mentor,´´ ``cognizant tool,´´ ``problem-solving partner,´´ and ``learner.´´ The first phase serves to introduce the problem space, with the computer initiating as well as responding to inquiries. In the second phase, the computer provides the student with a set of tools which amplify his problem-solving ability. The third phase employs the computer as a partner, supporting a joint problem-solving endeavor. Finally, the computer plays the role of a learner, and the student learns by teaching it how to solve new problems. Each phase has an analog in general problem-solving techniques, namely, problem representation, heuristic search, directed search, and formal algorithmic expression. Taken together, the four phases comprise an integrated educational system for using AI in CAI. The system is illustrated within the problem space of cryptography, and applications to several other subject areas are cited.