Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

From Complexity to Parsimony: Integrating Latent Class Analysis to Uncover Multimodal Learning Patterns in Collaborative Learning

Lixiang Yan, Dragan Gašević, Linxuan Zhao, Vanessa Echeverria, Yueqiao Jin, Roberto Martinez-Maldonado

TL;DR

A novel methodology for integrating latent class analysis (LCA) within MMLA to map monomodal behavioural indicators into parsimonious multimodal ones, finding that the multimodal approach was more parsimonious while offering higher explanatory power regarding students’ task and collaboration performances.

Abstract

Multimodal Learning Analytics (MMLA) leverages advanced sensing technologies and artificial intelligence to capture complex learning processes, but integrating diverse data sources into cohesive insights remains challenging. This study introduces a novel methodology for integrating latent class analysis (LCA) within MMLA to map monomodal behavioural indicators into parsimonious multimodal ones. Using a high-fidelity healthcare simulation context, we collected positional, audio, and physiological data, deriving 17 monomodal indicators. LCA identified four distinct latent classes: Collaborative Communication, Embodied Collaboration, Distant Interaction, and Solitary Engagement, each capturing unique monomodal patterns. Epistemic network analysis compared these multimodal indicators with the original monomodal indicators and found that the multimodal approach was more parsimonious while offering higher explanatory power regarding students' task and collaboration performances. The findings highlight the potential of LCA in simplifying the analysis of complex multimodal data while capturing nuanced, cross-modality behaviours, offering actionable insights for educators and enhancing the design of collaborative learning interventions. This study proposes a pathway for advancing MMLA, making it more parsimonious and manageable, and aligning with the principles of learner-centred education.

From Complexity to Parsimony: Integrating Latent Class Analysis to Uncover Multimodal Learning Patterns in Collaborative Learning

TL;DR

A novel methodology for integrating latent class analysis (LCA) within MMLA to map monomodal behavioural indicators into parsimonious multimodal ones, finding that the multimodal approach was more parsimonious while offering higher explanatory power regarding students’ task and collaboration performances.

Abstract

Multimodal Learning Analytics (MMLA) leverages advanced sensing technologies and artificial intelligence to capture complex learning processes, but integrating diverse data sources into cohesive insights remains challenging. This study introduces a novel methodology for integrating latent class analysis (LCA) within MMLA to map monomodal behavioural indicators into parsimonious multimodal ones. Using a high-fidelity healthcare simulation context, we collected positional, audio, and physiological data, deriving 17 monomodal indicators. LCA identified four distinct latent classes: Collaborative Communication, Embodied Collaboration, Distant Interaction, and Solitary Engagement, each capturing unique monomodal patterns. Epistemic network analysis compared these multimodal indicators with the original monomodal indicators and found that the multimodal approach was more parsimonious while offering higher explanatory power regarding students' task and collaboration performances. The findings highlight the potential of LCA in simplifying the analysis of complex multimodal data while capturing nuanced, cross-modality behaviours, offering actionable insights for educators and enhancing the design of collaborative learning interventions. This study proposes a pathway for advancing MMLA, making it more parsimonious and manageable, and aligning with the principles of learner-centred education.

Paper Structure

This paper contains 23 sections, 5 figures.

Table of Contents

  1. Introduction
  2. Background
  3. Complexity of Collaborative Learning
  4. Multimodal Learning Analytics and Data Fusion
  5. Latent Class Analysis
  6. Research Questions
  7. Method
  8. Learning Setting and Data
  9. Proposed Methodology: Mapping Multimodal Indicators
  10. From theory to monomodal indicators
  11. Eight task prioritisation indicators.
  12. Seven team communication indicators.
  13. Two physiological indicators.
  14. Synchronising Monomodal Behavioural Indicators
  15. Categorising Multimodal Behavioural Indicators
  16. ...and 8 more sections

Figures (5)

  • Figure 1: Mapping from sensory data to monomodal behavioural codes and then to multimodal behavioural codes.
  • Figure 2: Illustration of A) synchronising positioning, audio, and physiological data into 60-second intervals and B) categorising each learner (e.g., S1) at a given 60-second interval (e.g., T1) into a distinct latent class based on their behaviour patterns (e.g., [1,0,...,0,1]).
  • Figure 3: Four latent classes of multimodal behaviours (1 - present; 0 - absent), including Collaborative Communication (top-left), Embodied Collaboration (top-right), Distant Interaction (bottom-left), and Solitary Engagement (bottom-right).
  • Figure 4: Comparison of epistemic networks generated from 17 monomodal (left) and four multimodal behavioural codes (right) for students with low (red) and high (blue) task performance satisfaction.
  • Figure 5: Comparison of epistemic networks generated from 17 monomodal (left) and four multimodal behavioural codes (right) for students with low (red) and high (blue) collaboration performance satisfaction.