Learning Analytics for Concept Map Analysis

Primary supervisor

Roberto Martinez-Maldonado

This project focuses on the learning analytics of concept maps created by students in individual or collaborative learning settings. The central aim is to analyse the structure, semantics, and evolution of concept maps as representations of students’ knowledge. The project will explore how computational methods can be used to model learning processes and epistemic development through these artefacts.

Depending on your research trajectory, you may investigate questions such as:

  • How can learning analytics techniques be applied to automatically extract and model the semantic and structural features of concept maps?

  • How can epistemic network analysis (ENA) be used to represent the relationships among concepts and measure shifts in students’ understanding?

  • How do the topological and linguistic properties of concept maps differ between high- and low-achieving students?

  • How does collaborative editing of concept maps reflect knowledge co-construction, leadership, and epistemic agency?

  • What visual analytics methods can support teachers in interpreting patterns of knowledge construction in students’ concept maps?

 

Aim/outline

Methodological Approaches

Depending on your interests and background, the project may include:

  • Graph-theoretical analysis of concept map structure (e.g., density, centrality, modularity).

  • Natural Language Processing (NLP) for analysing concept labels and links.

  • Epistemic Network Analysis (ENA) to model the co-occurrence of concepts and links as indicators of epistemic constructs.

  • Machine learning approaches to classify and predict patterns of knowledge construction.

  • Visual analytics design to represent the evolution of knowledge networks over time.

URLs/references

Illustrative References

  • Martinez-Maldonado, R. et al. (2018). From Touches to Teamwork Constructs: Towards Automatically Visualising Collaboration Processes. Seventh Mexican Conference on Human-Computer Interaction (MexIHC 2018).

  • Shaffer, D. W., & Ruis, A. R. (2017). Epistemic Network Analysis: A Worked Example of Theory-Based Learning Analytics. In Handbook of Learning Analytics.

Required knowledge

Essential skills and dispositions:

  • Analytical, creative, and innovative approach to solving problems

  • Strong interest in learning analytics

  • Experience with data analytics or programming tools (e.g., Python))

Advantageous if you can evidence:

  • Familiarity with educational theory or learning sciences (especially conceptual learning)

  • Experience with visualisation or user-centred software design

  • Background in NLP, text mining, or basic data analysis