The Role of Cognitive Models in Automatic Item Generation
Mark J. Gierl, Hollis Lai · 2016
Automatic item generation is the process of using models to generate test items with the aid of computer technology. The purpose of this chapter is to describe and illustrate the important role that cognitive models play in the item generation process. A cognitive model for automatic item generation is a representation that highlights the knowledge, skills, competencies, and/or content required to generate new test items. Two types of cognitive models are presented. The first is the logical structures cognitive model. It is used when a specific concept or a set of closely related concepts is operationalized as part of the generative process. This model is often used to implement a main idea, formula, algorithm, and/or logical outcome. The second is the key features cognitive model. It is used when the attributes or features of a task are systematically combined to produce meaningful outcomes across the item feature set. This model is most suitable for measuring students’ ability to assemble and apply key features within a domain as well as to solve problems using these key features. An application of each model is presented using a practical example from K–12 science and medicine.