One of the main aims of a tutoring system is to assist the student in the learning process. There is no design process or method that can predict the outcomes or pre-empt all the learner’s problems; therefore, the design process must be iterative. A traditional software engineering model of life cycle, such as the waterfall model does not provide us with such flexibility. Therefore, the development of an intelligent tutoring system, requires a higher order iteration.

http://www.ifets.info/journals/3_3/virvou.html

Thanks Krishnan for your reply. I agree with you regarding the suitability of iterative development approach. But that was not the purpose of my question. 

I am trying to find out the pedagogical bases for current ITSs. For instance, learning theories used in ITSs (behavioral, cognitive, etc.)? I was not able to find such research papers, can you help in this regard?

Many thanks 

Rawad

Many factors determine whether the students in your classes will be motivated or not motivated to learn.

https://college.cengage.com/education/pbl/tc/motivate.html

Thanks Krishnan. But still motivation is part of the answer, sorry for that. We need to know if new ITSs are supporting collaborative learning theory? if ITSs use constructivist learning approaches? etc.

Thanks

No tutoring system can be as intelligent without a "real tutor interface". All IT enabled teaching and learning systems are confined to a particular set of knowledge base attached to it, being probed by a "Keyword search" or a "string search" options into the knowledge database.

Over a period of implementations it can be fine tuned.

with regards to motivation, it should be an economical advantage to the "content contributor". However, in a business model, the content provider is paid and forgotten as the site goes alive and the technical team takes charge of support and maintenance.