"Intelligent tutoring systems are quite difficult and time intensive to develop. In this paper, we describe a method and set of software tools that ease the process of cognitive task analysis and tutor development by allowing the author to demonstrate, instead of programming, the behavior of an intelligent tutor. We focus on the subset of our tools that allow authors to create “Pseudo Tutors” that exhibit the behavior of intelligent tutors without requiring AI programming. Authors build user interfaces by direct manipulation and then use a Behavior Recorder tool to demonstrate alternative correct and incorrect actions. The resulting behavior graph is annotated with instructional messages and knowledge labels. We present some preliminary evidence of the effectiveness of this approach, both in terms of reduced development time and learning outcome. Pseudo Tutors have now been built for economics, analytic logic, mathematics, and language learning. Our data supports an estimate of about 25:1 ratio of development time to instruction time for Pseudo Tutors, which compares favorably to the 200:1 estimate for Intelligent Tutors, though we acknowledge and discuss limitations of such estimates."
Kenneth R. Koedinger , Vincent Aleven , Neil Heffernan , Bruce McLaren , Matthew Hockenberry
1. SUMMARY
The paper focuses on the Cognitive Tutor Authoring Tool (CTAT) which allows the creation of intelligent tutor behavior without programming. It is said to be 8 times faster to develop than regular intelligent tutor (based on a preliminary result from a small development project. It based on Pseudo tutor which emulates the intelligent behaviors of true intelligent tutor and does so without using AI code. The compromise in Pseudo tutor’s capability can be compensated by faster development time and less cost. The basic step are: 1. Designing a graphical interface 2. Use the Behavior Recorder tool to construct state maps 3. Annotate state maps (with feedback, instructions, error messages, etc) 4. Adding knowledge labels 5. Inspect skill matrix and revise tutor design.
2. STRENGTHS
This method can be used by designers with no programming experience. CTAT can later be extended from Pseudo tutor to Cognitive tutor. Development time can be significantly lower than other methods. The process is well designed, with a functional software. The paper was well written and very easy to read.
3. WEAKNESSES
The paper admitted that formal data on development time were not collected. Pseudo tutors are in very early phase and cannot be applied to actual extensive classroom use. The paper also admitted that Pseudo tutor is not practical for scaling to large intelligent tutoring systems where variations of problems are massive.
