BOBCAT: Bilevel Optimization-Based Computerized Adaptive Testing
This work addresses the need for more efficient and personalized testing in education, representing a novel method for a known bottleneck.
The paper tackles the problem of improving computerized adaptive testing by learning a data-driven question selection algorithm from training data, resulting in BOBCAT outperforming existing methods in reducing test length across five real-world datasets.
Computerized adaptive testing (CAT) refers to a form of tests that are personalized to every student/test taker. CAT methods adaptively select the next most informative question/item for each student given their responses to previous questions, effectively reducing test length. Existing CAT methods use item response theory (IRT) models to relate student ability to their responses to questions and static question selection algorithms designed to reduce the ability estimation error as quickly as possible; therefore, these algorithms cannot improve by learning from large-scale student response data. In this paper, we propose BOBCAT, a Bilevel Optimization-Based framework for CAT to directly learn a data-driven question selection algorithm from training data. BOBCAT is agnostic to the underlying student response model and is computationally efficient during the adaptive testing process. Through extensive experiments on five real-world student response datasets, we show that BOBCAT outperforms existing CAT methods (sometimes significantly) at reducing test length.