Modeling MOOC learnflow with Petri net extensions

TL;DR

This paper introduces Petri nets with reference data (PNRDs) as a novel modeling approach for MOOC learnflows, enabling representation of multi-course programs, adaptive learning, and online collaboration.

Contribution

The paper proposes PNRDs, an extension of Petri nets, to effectively model complex, multi-agent, and adaptive MOOC education processes.

Findings

PNRDs effectively model multi-course MOOC programs.

PNRDs visualize dynamic changes in learning processes.

Application to online collaboration demonstrates PNRDs' versatility.

Abstract

Modern higher education takes advantage of MOOC technology. Modeling an education process of Massive open online courses (MOOCs) as a dynamic and multi-agent process is one of the challenging tasks. In this paper, Petri net extensions are investigated in the context of the learnflow modeling. It is shown how a learnflow can be modeled with classical and Colored Petri nets. These extensions facilitate modeling distributed and multi-agent processes. However, existing Petri net extensions do not provide the ability to model an education process in the context of multi-course programs and adaptive learning. We propose \emph{Petri nets with reference data} (PNRDs) for modeling e-learning in MOOCs. PNRDs allow us to represent a model of the education process in a visual, clear and not overloaded form. Moreover, PNRDs enable us to display aspects of multi-course programs and dynamic changes in the MOOC education process. We also show how PNRDs can be used to model online student collaboration in project-based learning.