Probabilistic Models for Computerized Adaptive Testing

TL;DR

This paper explores three models for computerized adaptive testing, including established item response theory and novel Bayesian and neural network approaches, analyzing their advantages, data application, and future research directions.

Contribution

Introduces two new models for CAT based on Bayesian networks and neural networks, expanding the methodological toolkit beyond traditional item response theory.

Findings

Item response theory effectively models student responses.

Bayesian and neural network models show promise for adaptive testing.

Data from paper tests validate the models' applicability.

Abstract

In this paper we follow our previous research in the area of Computerized Adaptive Testing (CAT). We present three different methods for CAT. One of them, the item response theory, is a well established method, while the other two, Bayesian and neural networks, are new in the area of educational testing. In the first part of this paper, we present the concept of CAT and its advantages and disadvantages. We collected data from paper tests performed with grammar school students. We provide the summary of data used for our experiments in the second part. Next, we present three different model types for CAT. They are based on the item response theory, Bayesian networks, and neural networks. The general theory associated with each type is briefly explained and the utilization of these models for CAT is analyzed. Future research is outlined in the concluding part of the paper. It shows many interesting research paths that are important not only for CAT but also for other areas of artificial intelligence.