As a contribution to Learning Analytics research, we will discuss theoretical frameworks for analyzing the log data of collaborative learning activities. More specifically, we argue that the frameworks of higher-order temporal networks, especially hypernetworks or simplicial complexes, are more appropriate than the ones of the traditional static frameworks. Network sciences provide the current frameworks used in the fields of learning sciences and educational technology to analyze cooperative learnings. However, the frameworks used in those fields are somewhat old-fashioned. Since learnings are essentially temporal (timedependent) and dynamical phenomena, analysis using static network models inevitably misses the essences of learnings. In the field of network sciences, the focus of research has shifted to more complex higher-order temporal networks. The mathematical frameworks of higher-order temporal networks, i.e., hypernetworks and simplicial complexes, allow us to analyze many body interacting systems. In addition, structural differences between hypernetworks and simplicial complexes, which were previously thought to be trivial, have been found to cause significant differences in dynamic phenomena. Interactions between learners observed in cooperative learnings are almost never one-to-one, but many-body ones such as one-to-many or many-to-many in group behaviors. Therefore, the appropriate theoretical frameworks must be higher-order temporal networks, not static network models. It is important to introduce these theoretical frameworks into the analysis of cooperative learning for the next development of Learning Analytics. In this presentation, we will discuss the next step of Learning Analytics in light of these recent results.

Authors: Koichi Yasutake, Hitoshi Inoue, Takahiro Tagawa, Osamu Yamakawa, Takahiro Sumiya

Published in: International Conference on Information Society (i-Society-2024)

• Date of Conference: 26-28 August, 2024
• DOI: 10.20533/iSociety.2024.0005
• ISBN: 978-1-913572-72-3
• Conference Location: Churchill College, Cambridge, UK