Designing Prompt Analytics Dashboards to Analyze Student-ChatGPT Interactions in EFL Writing
Project Overview
The document explores the incorporation of ChatGPT, a generative AI, in English as a Foreign Language (EFL) writing education, detailing its advantages and challenges. It introduces a Prompt Analytics Dashboard (PAD) designed to aid teachers in analyzing student interactions with ChatGPT, thereby offering valuable insights for improving teaching methods and student learning outcomes. Key applications include utilizing AI to enhance writing skills and provide personalized feedback, but the study also highlights significant concerns such as plagiarism, the potential for biased AI-generated responses, and the necessity for contextual understanding in AI-assisted learning environments. Overall, the findings underscore the transformative potential of generative AI in education while also calling attention to the need for careful implementation and monitoring to mitigate associated risks.
Key Applications
Prompt Analytics Dashboard (PAD)
Context: EFL writing classes for university students
Implementation: Developed through a design process involving interviews with teachers and prototype demonstrations during semester-long courses.
Outcomes: Helps teachers analyze student behaviors, design learning loops, and enhance teaching skills.
Challenges: Challenges include detecting plagiarism, managing additional workload, and ensuring the reliability of AI-generated content.
Implementation Barriers
Technical
The presence of inaccuracies and biases in AI-generated content can mislead students and teachers.
Proposed Solutions: Implementing robust mechanisms for plagiarism detection, developing guidelines for ethical AI usage in education, and ensuring the accuracy of AI outputs.
Workload
Teachers face increased workload from monitoring student interactions and adapting teaching methods.
Proposed Solutions: The PAD aims to streamline analysis and provide automated insights to reduce manual tasks.
Privacy
Concerns about students' sensitive information potentially being exposed through AI interactions.
Proposed Solutions: Establish strict data privacy protocols and educate students on responsible usage of AI tools.
Project Team
Minsun Kim
Researcher
SeonGyeom Kim
Researcher
Suyoun Lee
Researcher
Yoosang Yoon
Researcher
Junho Myung
Researcher
Haneul Yoo
Researcher
Hyunseung Lim
Researcher
Jieun Han
Researcher
Yoonsu Kim
Researcher
So-Yeon Ahn
Researcher
Juho Kim
Researcher
Alice Oh
Researcher
Hwajung Hong
Researcher
Tak Yeon Lee
Researcher
Contact Information
For information about the paper, please contact the authors.
Authors: 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
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