Lai Hollis, Gierl Mark J, Byrne B Ellen, Spielman Andrew I, Waldschmidt David M
Dr. Lai is Assistant Professor, University of Alberta School of Dentistry; Dr. Gierl is Professor and Canada Research Chair in Educational Measurement, University of Alberta Faculty of Education; Dr. Byrne is Professor of Endodontics and Senior Associate Dean, Virginia Commonwealth University School of Dentistry; Dr. Spielman is Professor and Associate Dean for Academic Affairs, New York University College of Dentistry; and Dr. Waldschmidt is Director of Testing Services, American Dental Association and Secretary of the Joint Commission on National Dental Examinations.
J Dent Educ. 2016 Mar;80(3):339-47.
Test items created for dentistry examinations are often individually written by content experts. This approach to item development is expensive because it requires the time and effort of many content experts but yields relatively few items. The aim of this study was to describe and illustrate how items can be generated using a systematic approach. Automatic item generation (AIG) is an alternative method that allows a small number of content experts to produce large numbers of items by integrating their domain expertise with computer technology. This article describes and illustrates how three modeling approaches to item content-item cloning, cognitive modeling, and image-anchored modeling-can be used to generate large numbers of multiple-choice test items for examinations in dentistry. Test items can be generated by combining the expertise of two content specialists with technology supported by AIG. A total of 5,467 new items were created during this study. From substitution of item content, to modeling appropriate responses based upon a cognitive model of correct responses, to generating items linked to specific graphical findings, AIG has the potential for meeting increasing demands for test items. Further, the methods described in this study can be generalized and applied to many other item types. Future research applications for AIG in dental education are discussed.
为牙科考试编写的测试项目通常由内容专家单独撰写。这种项目开发方法成本高昂，因为它需要许多内容专家投入时间和精力，但产出的项目相对较少。本研究的目的是描述和说明如何使用系统方法生成项目。自动项目生成（AIG）是一种替代方法，它允许少数内容专家通过将他们的领域专业知识与计算机技术相结合来生成大量项目。本文描述并说明了项目内容的三种建模方法——项目克隆、认知建模和图像锚定建模——如何用于为牙科考试生成大量多项选择题。通过将两位内容专家的专业知识与AIG支持的技术相结合，可以生成测试项目。在本研究期间共创建了5467个新项目。从替换项目内容，到基于正确答案的认知模型对适当答案进行建模，再到生成与特定图形结果相关的项目，AIG有潜力满足对测试项目不断增长的需求。此外，本研究中描述的方法可以推广并应用于许多其他项目类型。还讨论了AIG在牙科教育中的未来研究应用。
