The Q-matrix method of fault-tolerant teaching in knowledge assessment and data mining.

摘要

Fault tolerant teaching (FTT) systems are adaptive teaching systems that tolerate student, teacher, and system errors in diagnosing student misconceptions. These systems automatically assess student knowledge of the concepts underlying a tutorial topic, and use this assessment to direct remediation of knowledge. FTT methods use statistical techniques to interpret student responses to questions, and are constructed to tolerate the usual errors that occur during student testing—such as a student answering a question correctly without knowing how, or accidentally missing a question they understand well. These methods do not require any knowledge about the subject area being taught.; In this dissertation, we implement the q-matrix method of FTT in three NovaNET tutorials, covering three topics and several levels of difficulty. During the course of the experiment, a q-matrix model was constructed to explain the relationship between tutorial questions and the concepts underlying these questions. The q-matrix model was then used to assess student knowledge of each concept, and to guide their remediation. The learning paths of self-guided students were compared to those prescribed by the FTT system, to determine if a student's self-assessment corresponds to that made by the system. We evaluate the q-matrix model in terms of interpretability and its correspondence to expert models of the topics. We also compare the q-matrix extraction method to other data mining techniques, such as cluster analysis and factor analysis.; This dissertation resulted in the construction of a fully automated, fault tolerant, intelligent tutoring system, which can diagnose and correct student misconceptions. This system also provides a model for each topic that relates each tutorial question to its underlying concepts. The experimental analysis provides valuable insight into the factors that influence the extraction and interpretability of these models, as well as their value in automatically assessing student knowledge. In addition, the q-matrix method is used as a general data mining tool in one tutorial where a traditional application of the q-matrix method would not be appropriate. This application and its favorable comparison with other data mining tools mark the q-matrix method as a viable data clustering and interpretation tool for data mining.