Gierl Mark J, Lai Hollis
University of Alberta, Edmonton, Canada.
Appl Psychol Meas. 2018 Jan;42(1):42-57. doi: 10.1177/0146621617726788. Epub 2017 Aug 26.
Computerized testing provides many benefits to support formative assessment. However, the advent of computerized formative testing has also raised formidable new challenges, particularly in the area of item development. Large numbers of diverse, high-quality test items are required because items are continuously administered to students. Hence, hundreds of items are needed to develop the banks necessary for computerized formative testing. One promising approach that may be used to address this test development challenge is automatic item generation. Automatic item generation is a relatively new but rapidly evolving research area where cognitive and psychometric modeling practices are used to produce items with the aid of computer technology. The purpose of this study is to describe a new method for generating the items and the rationales required to solve the items to produce the required feedback for computerized formative testing. The method for rationale generation is demonstrated and evaluated in the medical education domain.
计算机化测试为支持形成性评估带来了诸多益处。然而，计算机化形成性测试的出现也带来了巨大的新挑战，尤其是在试题开发领域。由于需要持续向学生提供试题，所以需要大量多样、高质量的测试题。因此，开发计算机化形成性测试所需的题库需要数百道试题。一种有望用于应对这一测试开发挑战的方法是自动试题生成。自动试题生成是一个相对较新但发展迅速的研究领域，它利用认知和心理测量建模方法借助计算机技术来生成试题。本研究的目的是描述一种生成试题以及解答这些试题所需的原理依据的新方法，以便为计算机化形成性测试提供所需的反馈。在医学教育领域对原理依据生成方法进行了演示和评估。
