Implementation of motivational tactics in tutoring systems

The explicit teaching knowledge implemented in the current generation of Intelligent Tutoring Systems (ITSs) concerns mostly domain-based aspects of instructional processes, overlooking motivational aspects. This paper describes an instructional planner able to make decisions (about the next task to do, whether to provide hints, etc.) in order to achieve two goals: traversing the domain  domain-based planning  and maintaining the learner’s optimal motivational state  motivational planning. The traditional ITS architecture is extended to include the activities of motivational state modelling and motivational planning. For example, in motivational state modelling further learners’ characteristics are diagnosed, e.g. effort and confidence. Sometimes the advice offered by a motivational planner disagrees with a domain-based plan, while in other cases both plans complement each other. A method of negotiation between the motivational plan and the domain-based plan is provided in order to arrive at a decision for action by the tutor.