Network Motifs as Codes

I’ve been working on a framework of applying socio-semantic network analysis to discourse data.

Socio-semantic networks are two-mode, dual-layer networks that are made of actors (e.g., learners), semantic entities (e.g., words), and their relations. Socio-semantic network analysis brings together the study of relations among actors (human networks), relations among semantic elements (semantic networks), and relations among these two orders of networks (Basov et al., 2020). Such a dual-layer network analysis approach is not only useful for examining the duality of socio-semantic relations, it also applies to other settings such as socio-ecological analysis that’s interested in the interactions between social structures and ecological resources (Bodin & Tengö, 2012).

Socio-Semantic Network Motifs Framework for Discourse Analysis

ABSTRACT

Effective collaborative discourse requires both cognitive and social engagement of students. To investigate complex socio-cognitive dynamics in collaborative discourse, this paper proposes to model collaborative discourse as a socio-semantic network (SSN) and then use network motifs – defined as recurring, significant subgraphs – to characterize the network and hence the discourse. To demonstrate the utility of our SSN motifs framework, we applied it to a sample dataset. While more work needs to be done, the SSN motifs framework shows promise as a novel, theoretically informed approach to discourse analysis.

Networks in Learning Analytics: Where Theory, Methodology, and Practice Intersect

Keywords: network analysis, networked learning, social network analysis, learning analytics, network science, editorial

ABSTRACT

Network analysis has contributed to the emergence of learning analytics. In this editorial, we briefly introduce network science as a field and situate it within learning analytics. Drawing on the Learning Analytics Cycle, we highlight that effective application of network science methods in learning analytics involves critical considerations of learning processes, data, methods and metrics, and interventions, as well as ethics and value systems surrounding these areas. Careful work must meaningfully situate network methods and interventions within the theoretical assumptions explaining learning, as well as within pedagogical and technological factors shaping learning processes. The five empirical papers in the special section demonstrate diverse applications of network analysis, and the invited commentaries from cognitive network science and physics education research further discuss potential synergies between learning analytics and other sister fields with a shared interest in leveraging network science. We conclude by discussing opportunities to strengthen the rigour of network-based learning analytics projects, expand current work into nascent areas, and achieve more impact by holistically addressing the full cycle of learning analytics.

SoLAR Webinar: Analyzing Learning and Teaching through the Lens of Networks

A webinar exploring the conceptual, methodological, and practical use of networks in learning analytics by presenting examples from real-world learning and teaching scenarios that cover the following areas.