Intelligent tutoring systems work falls into three waves. The first wave involves basic research on technical implementation, including authoring systems and tutoring architectures. Second wave work takes this technological development beyond the laboratory. This work involves deep analysis of domain knowledge and empirical validation of systems. The emerging “third wave” takes advantage of widespread use of systems to refine and improve their effectiveness. Work in this area includes data mining and end-user authoring.
Although many types of systems have followed this evolution, intelligent tutoring systems are uniquely positioned among educational software to take advantage of the third wave. The architecture and authoring work from the first wave and the ability to incorporate domain knowledge and test pedagogical approaches in the second wave make us well positioned to ride this third wave.
In this talk, I will describe Carnegie Learning’s experience in riding these waves. We have taken intelligent tutoring systems for mathematics originally developed at Carnegie Mellon to scale with over 500,000 users per year, and are now riding the third wave to leverage this user base and improve the effectiveness and utility of our systems.
The final publication is available at Springer via https://doi.org/10.1007/978-3-642-13388-6_4.