Mia Stern

Adaptive Content in an Online Lecture System

This paper discusses techniques for adapting the content in an online lecture system for a specific user. A two pass method is used: 1) determine the appropriate level of difficulty for the student and 2) consider the students learning style preferences. A simple grading scheme is used to determine the students knowledge and a Naive Bayes Classifier is used to reason about the students preferences in terms of explanations, examples, and graphics. A technique for gathering and using population data is also discussed.

Using the Student Model to Control Problem Difficulty

We have created a student model which dynamically collects information about a student’s problem solving ability, acquisition of new topics and retention of earlier topics. This information is provided to the tutor and used to generate new problems at the appropriate level of difficulty and to provide customized hints and help. Formative evaluation of the tutor with 20 students provides evidence that the student model constructs problems at the correct level of difficulty. The problem generation technique is extensible for use in other problem-based domains. This paper describes the design and implementation of the student model and illustrates how the tutor adjusts the difficulty of a problem based on the student model.

Adaptation of Problem Presentation and Feedback in an Intelligent Mathematics Tutor

We have developed an intelligent tutor for teaching remedial mathematics to community college students. This domain is fairly narrow in scope and is an important component of the college curriculum. The target audience often retains fragments of knowledge from previous courses which can aid them in learning; alternately, misconceptions can present conceptual stumbling blocks if students have misremembered what they learned previously. Thus, a system built with a strong student model can greatly benefit the teaching process. The tutor described in this paper tracks student skills along with a general acquisition factor, and uses this information for topic selection, problem generation, problem presentation, and dynamic feedback.

Workshop I - Intelligent Tutoring Systems on the Web

Educational material has begun to proliferate on the World Wide Web. However, most of these applications are rather simple, providing little interaction or customization for students. A promising approach to Web-based education is the use of intelligent Web-based systems. In this workshop, we investigate the application of intelligent tutoring systems on the Web and bring together researchers who have had and can share their experiences in developing Web-based intelligent tutoring systems. Some of the questions we address concern the specific problems and advantages of the Web for intelligent tutoring systems. In particular, we address topics such as: How can we increase interactivity on the Web? How can we overcome delays due to downloading? Where will the intelligence be located? On the client? The server? A mix of both? What kind of intelligence can be used? Can we build systems as smart as our standalone systems? What type of connectivity and communication is possible between intelligent systems?