Beverly Woolf asks in the last section of her book Building Intelligent Interactive Tutors: Student-centered strategies for revolutionizing e-learning” a very intriguing question. A question which relates to why a project like I-TUTOR is needed.
She asks, after having described methods for creating intelligent tutors, why there really aren’t many of them in existence? The impact of these could after all be huge, and there ought to be a repository somewhere with various different tutor systems.
Beverly answers this herself. These systems requires a lot of man hours to develop, often ~200 hours of development for 1 hours of tutorial. Therefore few are developed and even fewer are shared.
One could now ask: Why does the I-TUTOR project dare to work on this area?
Well, granted it might seem like a big task, but, there is one main difference. This project is not working on any content based tutorial. We are not making tutorial about Chemistry, Programming or Linguistics. We are investigating the possibilities of create intelligent tutor support by looking at meta-learning. How a student performs in a module is very likely correlated to certain ways that the students interacts with the VLE, for instance frequency of usage, posts made, forum questions etc. This is a different level of information, which can be made inferences on at a different level than what you do when you create a bespoke tutorial for a specific module. A different level, which potentially will be transferable between subjects, institutions and nationalities.