A Survey of Models for Cognitive Diagnosis: New Developments and Future Directions

TL;DR

This paper surveys recent models for cognitive diagnosis, emphasizing machine learning approaches, compares their structures and algorithms, and discusses future research directions, while providing Python tools for data access and model implementation.

Contribution

It offers a comprehensive review of current cognitive diagnosis models, especially new machine learning-based methods, and introduces two Python libraries for data and model applications.

Findings

Comparison of model structures and algorithms

Overview of recent trends in cognitive diagnosis

Introduction of Python libraries for data and models

Abstract

Cognitive diagnosis has been developed for decades as an effective measurement tool to evaluate human cognitive status such as ability level and knowledge mastery. It has been applied to a wide range of fields including education, sport, psychological diagnosis, etc. By providing better awareness of cognitive status, it can serve as the basis for personalized services such as well-designed medical treatment, teaching strategy and vocational training. This paper aims to provide a survey of current models for cognitive diagnosis, with more attention on new developments using machine learning-based methods. By comparing the model structures, parameter estimation algorithms, model evaluation methods and applications, we provide a relatively comprehensive review of the recent trends in cognitive diagnosis models. Further, we discuss future directions that are worthy of exploration. In addition, we release two Python libraries: EduData for easy access to some relevant public datasets we have collected, and EduCDM that implements popular CDMs to facilitate both applications and research purposes.