Skip to main content Skip to navigation

When learning analytics dashboard is explainable: An exploratory study on the effect of GenAI-supported learning analytics dashboard

Project Overview

The document examines the role of generative AI in education, particularly through the use of a theory-driven, explainable Learning Analytics Dashboard (LAD) aimed at assisting university students with collaborative academic abstract writing. The study's findings suggest that while the quality of abstracts generated by students using the explainable LAD did not significantly surpass those produced with a visual-only version, the former group exhibited a more profound understanding of abstract writing principles. This highlights the value of explainable feedback in fostering self-regulated learning and improving students' conceptual comprehension of academic writing. Overall, the research underscores the potential of generative AI tools, such as the explainable LAD, to enhance educational outcomes by promoting deeper learning and self-awareness among students in the writing process.

Key Applications

Explainable Learning Analytics Dashboard (LAD)

Context: University students engaged in collaborative academic abstract writing tasks

Implementation: Participants were assigned to either an experimental group with a full explainable LAD or a control group with a visual-only LAD to write an academic abstract in collaboration with Generative AI.

Outcomes: Students using the explainable LAD scored significantly higher on a knowledge test regarding abstract writing principles, indicating better conceptual understanding.

Challenges: No significant differences in the quality of abstracts written by the two groups, suggesting that for short tasks, basic feedback may suffice.

Implementation Barriers

Understanding

Students may find the information on dashboards unclear or irrelevant, leading to a lack of trust and engagement.

Proposed Solutions: Integrating explainability into the dashboard design can help students understand how data is collected and how to act on it.

Project Team

Angxuan Chen

Researcher

Contact Information

For information about the paper, please contact the authors.

Authors: Angxuan Chen

Source Publication: View Original PaperLink opens in a new window

Project Contact: Dr. Jianhua Yang

LLM Model Version: gpt-4o-mini-2024-07-18

Analysis Provider: Openai

Let us know you agree to cookies