Using Knowledge Discovery Techniques to Support Tutoring in an Ill-Defined Domain

Domain experts should provide relevant knowledge to a tutoring system so that it can guide a learner during problem-solving learning activities. However, for ill-defined domains this knowledge is hard to define explicitly. As an alternative, this paper presents a framework to learn relevant knowledge related to procedural tasks from users’ solutions in an ill-defined procedural domain. The proposed framework is based on a combination of sequential pattern mining and association rules discovery. The resulting knowledge base allows the tutoring system to guide learners in problem-solving situations. Preliminary experiments have been conducted in CanadarmTutor.