A semi-supervised learning-based diagnostic classification method using artificial neural networks
Frontiers in Psychology, 11, 3992
The purpose of cognitive diagnostic modelling is to classify students’ latent attribute profiles using their responses to the diagnostic assessment. In recent years, each theoretical diagnostic classification model makes different assumptions about the relationship between a student’s response pattern and attribute profile. The previous research studies showed that the misspecification of TDCM and inaccurate Q-matrix impact classification accuracy. Artificial Neural Networks have been proposed as a promising approach to convert a pattern of item responses into a diagnostic classification in some research studies. However, the ANNs methods produced very unstable and unappreciated estimation unless a great deal of care was taken. In this research, we combined ANNs with two typical theoretical diagnostic classification models, the DINA model and DINO model, within a semi-supervised learning framework to achieve a robust and accurate classification. In both simulated study and real data study, the experimental results showed that the proposed method could achieve appreciated performance across different test conditions, especially when the diagnostic quality of assessment was not high and the Q-matrix contained misspecified elements. This research study is the first time of applying the thinking of semi-supervised learning into CDM. Also, we used the validating test to choose the appropriate parameters for the ANNs instead of using typical statistical criteria, such as AIC, BIC.See More
This article was published outside of NWEA. The full text can be found at the link above.
Topics: Measurement & scaling