Cognitive diagnosis models for learner profiling in lifelong learning

Abstract

The demands of global knowledge-based economy nowadays have shifted learning and training towards the lifelong learning paradigm. This new learning environment requires changes in educational assessment practices. On top of the norm-referenced type of assessment which prescribe learners with a single test score, mechanisms to recognize the skills acquired by learners to ensure the learners' progression from one level or one form of learning to another are highly needed. Currently, researchers in cognitive psychology and psychometrics have developed cognitive diagnosis models using responses to test items. With the highly computational capability, the cognitive diagnosis models can be applied in computer system and a profile of knowledge, skills and proficiencies acquired by each learner or learner profile can be prescribed. The purpose of this paper is to give an insight into some cognitive diagnosis models from the statistical and data mining perspectives. The strengths and limitations of the models are also exposed. This paper concludes with the potential of the models to act as learner profiling mechanism in the lifelong learning environment.