Bringing personalized learning into computer-aided question generation

TL;DR

This paper introduces a statistical ability estimation method based on acquisition distribution for personalized computer-aided question generation, demonstrating robustness and improved learner ability matching through empirical validation.

Contribution

It presents a novel ability estimation approach that adapts over time and is robust when learner ability is unknown, enhancing personalized question generation.

Findings

Estimated abilities match actual learner abilities

Significant improvement in pretest and post-test scores

Method is robust and adaptable for personalized testing

Abstract

This paper proposes a novel and statistical method of ability estimation based on acquisition distribution for a personalized computer aided question generation. This method captures the learning outcomes over time and provides a flexible measurement based on the acquisition distributions instead of precalibration. Compared to the previous studies, the proposed method is robust, especially when an ability of a student is unknown. The results from the empirical data show that the estimated abilities match the actual abilities of learners, and the pretest and post-test of the experimental group show significant improvement. These results suggest that this method can serves as the ability estimation for a personalized computer-aided testing environment.