BOBCAT: Bilevel Optimization-Based Computerized Adaptive Testing
BOBCAT: Bilevel Optimization-Based Computerized Adaptive Testing
复制标题
DOI：
10.24963/ijcai.2021/332
复制
发表时间：
2021-08
期刊：
影响因子：
--
通讯作者：
Aritra Ghosh;Andrew S. Lan
中科院分区：
文献类型：
--
作者：
Aritra Ghosh;Andrew S. Lan
计算机化自适应测试（CAT）是指一种针对每个学生/考生个性化的测试形式。CAT方法自适应地为每个学生选择下一个信息量最大的问题/项目，给出他们对之前问题的回答，有效地减少了测试长度。现有的CAT方法使用项目反应理论（IRT）模型，以学生的能力，他们对问题的反应和静态问题选择算法，旨在减少能力估计误差尽可能快，因此，这些算法不能提高从大规模的学生响应数据的学习。在本文中，我们提出了BOBCAT，一个基于双层优化的CAT框架，可以直接从训练数据中学习数据驱动的问题选择算法。BOBCAT对底层学生响应模型不可知，并且在自适应测试过程中计算效率很高。通过对五个真实世界学生响应数据集的广泛实验，我们表明BOBCAT在减少测试长度方面优于现有的CAT方法（有时显着）。
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.