Extracting Student Models for Intelligent Tutoring Systems
نویسندگان
چکیده
Intelligent Tutoring Systems (ITSs) that adapt to an individual student’s needs have been shown to be extremely effective, showing significant improvement in achievement over non-adaptive instruction (Murray 1999). The most successful of these systems require the construction of complex cognitive models that are applicable only to a specific tutorial in a specific field, requiring the time of experts to create and test these models on students. In order to achieve the benefits that ITSs provide, we must find a way to simplify their creation. Therefore, we are creating a framework to automate the generation of ITS student models. The goal is to provide a simple way to allow developers of computer-based training (CBT) to add adaptive capabilities with minimal work while still maintaining the effectiveness of a true ITS.
منابع مشابه
Characterizing the Effectiveness of Tutorial Dialogue with Hidden Markov Models
Identifying effective tutorial dialogue strategies is a key issue for intelligent tutoring systems research. Human-human tutoring offers a valuable model for identifying effective tutorial strategies, but extracting them is a challenge because of the richness of human dialogue. This paper addresses that challenge through a machine learning approach that 1) learns tutorial strategies from a corp...
متن کاملBypassing the Intractable Problem of Student Modelling
This paper attempts to rehabilitate student models within intelligent tutoring systems. Recently, some researchers have questioned both the need for detailed student models and the practical possibility of building them. We regard it as axiomatic that any intelligent tutoring system needs a student model. This paper suggests some practical guidelines and changes in philosophical approach which ...
متن کاملToward Automatic Hint Generation for Logic Proof Tutoring Using Historical Student Data
We have proposed a novel application of Markov decision processes (MDPs), a reinforcement learning technique, to automatically generate hints for an intelligent tutor that learns. We demonstrate the feasibility of this approach by extracting MDPs from four semesters of student solutions in a logic proof tutor, and calculating the probability that we will be able to generate hints at any point i...
متن کاملDiscourse Initiative: Its Role in Intelligent Tutoring Systems
Research suggests that a student who is actively involved in the learning process has a higher rate of achievement than does a student who is merely a passive recipient of information. Active learning implies that the student will occasionally take the discourse initiative and attempt to shape the information provided by the instructor. However, relatively little attention has been given to the...
متن کاملBayesian Student Modeling
Bayesian networks are a formalism for reasoning under uncertainty that has been widely adopted in Artificial Intelligence (AI). Student modeling, i.e., the process of having an ITS build a model of relevant student’s traits/states during interaction, is a task permeated with uncertainty, which naturally calls for probabilistic approaches. In this chapter, I will describe techniques and issues i...
متن کامل