ADVANCES IN LOCAL STUDENT MODELING USING INFORMAL FUZZY-REASONING

This paper presents an approach to local student modeling in mathemati cs intelligent tutors. A knowledge representation is developed that st ores separately the semantic and structural information needed to repr esent math word problems. Based on this representation, and the assign ment of weights to semantic labels for problem sets, the student is al lowed considerable flexibility in the development of solutions. The te chnique used in matching student solutions to acceptable solutions is based on imprecision or fuzziness, i.e. exact matches to stored soluti ons are not required. Moreover, this imprecise approach, together with a ''collapsing'' of the tree of all possible solutions, substantially reduces storage and search requirements, addressing some combinatoria l explosion and speed problems of modeling. This method can support a variety of instructional strategies. (C) Academic Press Limited