Multilayer Network Analysis of Learner Interaction in Digital Smart Technology-Enhanced Heterogeneous Learning Environments—Application and Prospects Based on the Traces Analysis Framework
Multilayer Network Analysis of Learner Interaction in Digital Smart Technology-Enhanced Heterogeneous Learning Environments—Application and Prospects Based on the Traces Analysis Framework
In the era of smart and digital learning,education is increasingly characterized by open,diverse learning spaces,complex and nonlinear processes,and the growing social,intelligent,contextual,and networked nature of learning.The learning con-text is a complex system where continuous behavioral data,varying in granularity,are dispersed across heterogeneous environments.Linking these data is crucial for developing a continuous understanding of learning behaviors and systematically identifying patterns in smart and digital contexts.The challenge of linking and analyzing dispersed interaction data is a key issue in learning analytics;and this study recognizes the multilayer network analysis method,the Traces framework,as a solution.This paper outlines the framework's features,core concepts,analytical processes at different levels,and supporting methods.Furthermore,through examples,it demon-strates that the Traces framework can be applied not only globally to identify interaction sessions,key participants,learner groups(communities),analyze relationships,and track evolving participation dynamics,but also locally for micro-level analysis.Additionally,this paper shows that the framework can span multiple smart and digital learning environments,integrating methods such as thread and social network analysis.It breaks through the limitations of one-dimensional and reductionist approaches by focusing on the com-plex relationships between actors and expanding the scope of analysis.The Traces framework,offering a new paradigm for educational research in the"data ocean"of the smart and digital era,is helpful for researchers to gain a continuous understanding of complex learning behaviors.It provides new methods for understanding the interactive dynamics in digital smart technology-enhanced learning environments and comprehending the complex patterns of learning in the digital age.
万方数据