Abstract:
At present, many educational researchers and practitioners are highly interested in using educational assessment to improve student learning. However, it should be noted that assessment and learning can exist as two distinct components, and require a framework that would allow their integration into a single coherent system. The efficiency of such a system will depend on the extent that each component can be implemented adaptively. In this presentation, I will discuss using cognitive diagnosis modeling as a framework for developing a personalize assessment and learning system (PALS). I will discuss what cognitive diagnosis models (CDMs) are, what their unique features are, how they differ from other psychometric models, and how cognitive diagnosis computerized adaptive testing can further capitalize on the advantages of CDMs and make diagnostic testing more efficient. To build the complete PALS, an explicit instructional component that can facilitate learning is needed. I will discuss a number of important issues that need to addressed before a coherent and effective PALS can be built. The presentation will conclude with a discussion of possible future directions, and some of the challenges and recent developments in the area.