A Collective Dynamic Indicator for Discussion Forums in Learning Management Systems

In today’s successful Learning Management System (LMS), gathering thousands of students, emergent collective dynamics drive innovative learning experiences where learners help each other in online forums. The benefits of those behaviors were theorized in Vygotsky’s socio-constructivism theory where he insists that the knowledge development of not so formal peer exchanges is beneficial to all participants. Observing and understanding how those dynamics occur could improve course design and help tutors intervene to sustain collective learning. But, although the scientific community acknowledges the importance of theses dynamics, few works have yet been able to grasp and display them in a format tailored to the Massive Open Online Courses (MOOCs)’ instructors. Indeed, only recently have researches been able to articulate the required continuous Natural Language Processing (NLP) and Social Network Analysis (SNA). In this research, we propose an innovative model to compute a collective activity indicator to answer the problem of detecting and visualizing the collective dynamics from the MOOCs’s forums interactions. We also present datasets collected from several LMSs and used to illustrate the portability, scalability, interactivity of our first visualizations. Our approach should help develop indicators and Learning Dashboard (LDB) of collective actions for MOOCs.