Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

LLM-Driven Learning Analytics Dashboard for Teachers in EFL Writing Education

Minsun Kim, SeonGyeom Kim, Suyoun Lee, Yoosang Yoon, Junho Myung, Haneul Yoo, Hyunseung Lim, Jieun Han, Yoonsu Kim, So-Yeon Ahn, Juho Kim, Alice Oh, Hwajung Hong, Tak Yeon Lee

TL;DR

It is demonstrated how a human-centered approach can enhance the effectiveness of teacher dashboards, particularly in ChatGPT-integrated learning.

Abstract

This paper presents the development of a dashboard designed specifically for teachers in English as a Foreign Language (EFL) writing education. Leveraging LLMs, the dashboard facilitates the analysis of student interactions with an essay writing system, which integrates ChatGPT for real-time feedback. The dashboard aids teachers in monitoring student behavior, identifying noneducational interaction with ChatGPT, and aligning instructional strategies with learning objectives. By combining insights from NLP and Human-Computer Interaction (HCI), this study demonstrates how a human-centered approach can enhance the effectiveness of teacher dashboards, particularly in ChatGPT-integrated learning.

LLM-Driven Learning Analytics Dashboard for Teachers in EFL Writing Education

TL;DR

It is demonstrated how a human-centered approach can enhance the effectiveness of teacher dashboards, particularly in ChatGPT-integrated learning.

Abstract

This paper presents the development of a dashboard designed specifically for teachers in English as a Foreign Language (EFL) writing education. Leveraging LLMs, the dashboard facilitates the analysis of student interactions with an essay writing system, which integrates ChatGPT for real-time feedback. The dashboard aids teachers in monitoring student behavior, identifying noneducational interaction with ChatGPT, and aligning instructional strategies with learning objectives. By combining insights from NLP and Human-Computer Interaction (HCI), this study demonstrates how a human-centered approach can enhance the effectiveness of teacher dashboards, particularly in ChatGPT-integrated learning.

Paper Structure

This paper contains 13 sections, 3 figures.

Table of Contents

  1. Introduction
  2. Related Work
  3. LLM applications for teachers
  4. Human-centered NLP (HCNLP)
  5. Human-Centered Learning Analytics (HCLA)
  6. Methodology for Human-Centered NLP
  7. Participants
  8. Progress
  9. Dashboard Prototype
  10. Dataset and models
  11. Feature description
  12. Discussion
  13. Conclusion

Figures (3)

  • Figure 1: Relationships and progress between experts and potential users in education.
  • Figure 2: A dashboard system architecture.
  • Figure 3: A dashboard prototype overview.