INSTRUCT - MODELING STUDENTS BY ASKING QUESTIONS

The paper reports an approach to inducing models of procedural skills from observed student performance. The approach, referred to as INSTRU CT, builds on two well-known techniques, reconstructive modeling and m odel tracing, at the same time avoiding their major pitfalls. INSTRUCT does not require prior empirical knowledge of student errors and is a lso neutral with respect to pedagogy and reasoning strategies applied by the student. Pedagogical actions and the student model are generate d on-line, which allows for dynamic adaptation of instruction, problem generation and immediate feedback on student's errors. Furthermore, t he approach is not only incremental but truly active, since it involve s students in explicit dialogues about problem-solving decisions. Stud ent behaviour is used as a source of information for user modeling and to compensate for the unreliability of the student model. INSTRUCT us es both implicit information about the steps the student performed or the explanations he or she asked for, and explicit information gained from the student's answers to direct question about operations being p erformed. Domain knowledge and the user model are used to focus the se arch on the portion of the problem space the student is likely to trav erse while solving the problem at hand. The approach presented is exam ined in the context of SINT, an ITS for the domain of symbolic integra tion.