Document Type

Report

Publication Date

11-2024

Abstract

Personalized Learning Paths (PLP)s are a popular area of research in E-Learning where sequences of Learning Materials (LM)s and activities are returned based on a learner profile, the LM metadata, and a knowledge structure that describes the relationship between the underlying topics. Unfortunately, PLP researchers tend to not use an empirically supported cognitive science framework for their research, instead relying on such unsupported theories as learning styles or developing their own ad hoc approaches. While many of these researchers present and solve challenging PLP problems using a variety of algorithmic approaches, the PLP community in general would benefit from a rubric that can be used to quantitatively assess the degree of fit of a PLP for a targeted learner based on an empirically supported cognitive science theory and a set of realistic use cases. This data package includes two rubrics based on the Cognitive Theory of Multimedia Learning (CTML) that are designed to serve this purpose for the PLP research community. CTML is a field of research in cognitive science that offers a set of empirically supported principles that provide insight into what LM and PLP characteristics are likely to improve learning outcomes. The rubrics offered in this data package are an initial attempt to quantify LMs and PLPs according to these CTML principles and are further informed by a small set of realistic learner use cases. The authors of these rubrics hope that they will lead to a publicly available set of labeled LM and PLP data that can benefit future E-Learning research. Researchers should consider using these rubrics to inform their PLP data structure and algorithmic designs and adapt them to their specific use cases when necessary.

Comments

Contents:

  • Learning Material CTML Rubric v1.2
  • PLP Rubric v1.2

Approved for public release, 88ABW-2024-0965

Download

Share

COinS