Mar 282011

 Intelligent Tutoring Systems

 …In the early 1970s a few researchers defined a new and ambitious goal for computer-based instruction. They adopted the human tutor as their educational model and sought to apply artificial intelligence techniques to realize this model in “intelligent” computer- based instruction. Personal human tutors provide a highly efficient learning environment (Cohen, Kulik and Kulik,1982) and have been estimated to increase mean achievement outcomes by as much as two standard deviations (Bloom, 1984)1.The goal of intelligent tutoring systems (ITSs) would be to engage the students in sustained reasoning activity and to interact with the student based on adeep understanding of the students behavior. If such systems realize even half the impact of human tutors, the payoff for society promised to be substantial…  

…While there has been a rich intellectual history in intelligent tutoring, we believe that for intelligent tutors to seriously penetrate the educational/training system, the evaluative focus must begin to shift to educational impact and away from artificial intelligence sufficiency…We believe the emphasis on educational impact must permeate all stages of ITS development, deployment and assessment…   

…These studies revealed early on the likely futility of building an intelligent tutor around an off-the shelf expert system. Instead, it is necessary to develop a true cognitive model of the domain knowledge that solves exercises in the same way students solve them. We refer to this domain expert as an ideal student model, since it is a computational model of the ideal knowledge the student is acquiring. As a result, one of the crucial steps in intelligent tutor development is a careful analysis of how humans, both expert and novice approach the problem solving task…  

…The Pedagogical Module. The pedagogical module is responsible for structuring the instructional interventions. This module may operate at two levels (Pirolli and Greeno, 1998). At the curriculum level it can sequence topics to ensure an appropriate prerequisite structure is observed (Capell and Dannenberg, 1993) and individualize the amount of practice at each level to ensure the students master the material (Corbett and Anderson, 1995b). At the problem solving support level, it can intervene to advise the student on problem solving activities. Towne and Munro (1992) outline five types of instructional interventions: 

(I) Performance demonstration – The program demonstrates a successful sequence of actions in a problem solving task.

(2) Directed step-by-step performance- The program provides a sequence of actions for the student to follow in a problem solving task.

(3) Monitored performance – The student solves a problem set by the program. The pro gram intervenes if the student makes mistakes or gets stuck.

 (4) Goal seeking – The student solves a problem set by the program. The program monitors the level of abstract problem states rather than individual actions.

(5) Free Exploration – The learner freely manipulates the problem solving environment.

A sixth condition may be included, one in which the program sets a problem solving task but does not provide support…  

Handbook of Human-Computer Interaction, Second, Completely Revised Edition in M. Helander, T. K. Landauer, P. Prabhu (Eds), Elsevier Science B. V., ©1997, Chapter 37; Albert T. Corbett and Kenneth R. Koedinger, Human Computer Interaction Institute, Carnegie Mellon University Pittsburgh, Pennsylvania, USA; John R. Anderson, Department of Psychology and Computer Science, Carnegie Mellon University. Pittsburgh, Pennsylvania, USA


To Discuss how these Solutions will add value for you, your organization and/or your clients, Affinity/Resale Opportunities, and/or Collaborative Efforts, Please Contact:

Tom McDonald,; 608-788-5144; Skype: tsmw5752

intelligent tutoring systems, McDonald Sales and Marketing, LLC