Heterogeneous Interaction Network Analysis (HINA): A New Learning Analytics Approach for Modelling, Analyzing, and Visualizing Complex Interactions in Learning Processes

2026-01-11

arXiv.org

AI Summary

This study addresses the limitations of existing learning analytics approaches in capturing the complexity and heterogeneity of multi-agent, multi-modal interactions in contemporary learning environments. To this end, it proposes HINA—a novel framework that introduces a heterogeneous interaction network paradigm, unifying diverse entities such as learners, behaviors, AI agents, and task designs into a single heterogeneous network model. By integrating non-parametric clustering, statistical testing, and interactive visualization, HINA establishes a multi-level analytical pipeline supporting individual, dyadic, and meso-level investigations. Applied to an AI-supported collaborative learning context, the framework successfully uncovers distinct interaction patterns, engagement profiles, and behavioral tendencies among students, their peers, and AI agents, thereby demonstrating its effectiveness and innovation in enabling unified modeling and deep analytical insights.

Technology Category

• Machine Learning: Multimodal Learning
• Multiagent Systems: Multiagent Learning
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Social networks and social learning
• User Modeling, Personalization and Recommendation: Practical large-scale studies of user experience

Abstract

Existing learning analytics approaches, which often model learning processes as sequences of learner actions or homogeneous relationships, are limited in capturing the distributed, multi-faceted nature of interactions in contemporary learning environments. To address this, we propose Heterogeneous Interaction Network Analysis (HINA), a novel multi-level learning analytics framework for modeling complex learning processes across diverse entities (e.g., learners, behaviours, AI agents, and task designs). HINA integrates a set of original methods, including summative measures and a new non-parametric clustering technique, with established practices for statistical testing and interactive visualization to provide a flexible and powerful analytical toolkit. In this paper, we first detail the theoretical and mathematical foundations of HINA for individual, dyadic, and meso-level analysis. We then demonstrate HINA's utility through a case study on AI-mediated small-group collaborative learning, revealing students'interaction profiles with peers versus AI; distinct engagement patterns that emerge from these interactions; and specific types of learning behaviors (e.g., asking questions, planning) directed to AI versus peers. By transforming process data into Heterogeneous Interaction Networks (HINs), HINA introduces a new paradigm for modeling learning processes and provides the dedicated, multi-level analytical methods required to extract meaning from them. It thereby moves beyond a single process data type to quantify and visualize how different elements in a learning environment interact and co-influence each other, opening new avenues for understanding complex educational dynamics.

Problem

• learning analytics
• heterogeneous interactions
• complex learning processes
• interaction modeling
• educational dynamics

Innovation

• Heterogeneous Interaction Network Analysis
• learning analytics
• non-parametric clustering
• multi-level analysis
• AI-mediated collaboration