Tutor Modeling Versus Student Modeling

AAAI Conferences

The current paradigm in student modeling has continued to show the power of its simplifying assumption of knowledge as a binary and monotonically increasing construct, the value of which directly causes the outcome of student answers to questions. Recent efforts have focused on optimizing the prediction accuracy of responses to questions using student models. Incorporating individual student parameter interactions has been an interpretable and principled approach which has improved the performance of this task, as demonstrated by its application in the 2010 KDD Cup challenge on Educational Data. Performance prediction, however, can have limited practical utility. The greatest utility of such student models can be their ability to model the tutor and the attributes of the tutor which are causing learning. Harnessing the same simplifying assumption of learning used in student modeling, we can turn this model on its head to effectively tease out the tutor attributes causing learning and begin to optimize the tutor model to benefit the student model.


Evaluating the Feasibility of Learning Student Models from Data

AAAI Conferences

Recent work on intelligent tutoring systems has used Bayesian networks to model students' acquisition of skills. In many cases, researchers have hand-coded the parameters of the networks, arguing that the conditional probabilities of models containing hidden variables are too difficult to learn from data. We present a machine learning approach that uses Expectation-Maximization to learn the parameters of a dynamic Bayesian network with hidden variables. We test our methodology on data that was simulated using a state-based model of skill acquisition. Results indicate that it is possible to learn the parameters of hidden variables given enough sequential data of training sessions on similar problems.


Cognitive Mastery Learning in the ACT Programming Tutor

AAAI Conferences

The ACT Programming Tutor (APT) is a problem solving environment constructed around an executable cognitive model of the programming knowledge students are acquiring. This cognitive model supports two types of adaptive instructional processes. First, it enables the tutor to follow each student's solution path through complex problem solving spaces, providing appropriate assistance as needed. Second, it enables the tutor to implement cognitive mastery learning in which fine-grained inferences about student knowledge are employed to adapt the problem sequence. This paper outlines the assumptions and procedures of cognitive mastery learning and describes evidence of its success in promoting student achievement. The paper also explores the limits of cognitive mastery as implemented in APT and begins to examine new directions.


Towards Data Driven Model Improvement

AAAI Conferences

In the area of student knowledge assessment, knowledge tracing is a model that has been used for over a decade to predict student knowledge and performance. Many modifications to this model have been proposed and evaluated, however, the modifications are often based on a combination of intuition and experience in the domain. This method of model improvement can be difficult for researchers without high level of domain experience and furthermore, the best improvements to the model could be unintuitive ones. Therefore, we propose a completely data driven approach to model improvement. This alternative allows for researchers to evaluate which aspects of a model are most likely to result in model performance improvement. Our results suggest a variety of different improvements to knowledge tracing many of which have not been explored.


ADVISOR: AMachine Learning Architecture forIntelligent TutorConstruction

AAAI Conferences

We have constructed ADVISOR, a two-agent machine learning architecture for intelligent tutoring systems (ITS). The purpose of this architecture is to centralize the reasoning of an ITS into a single component to allow customization of teaching goals and to simplify improving the ITS. The first agent is responsible for learning a model of how students perform using the tutor in a variety of contexts. The second agent is provided this model of student behavior and a goal specifying the desired educational objective. Reinforcement learning is used by this agent to derive a teaching policy that meets the specified educational goal.