Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Study on Educational Data Analysis and Personalized Feedback Report Generation Based on Tags and ChatGPT

Yizhou Zhou, Mengqiao Zhang, Yuan-Hao Jiang, Xinyu Gao, Naijie Liu, Bo Jiang

TL;DR

This paper addresses the challenge of turning rich educational data into timely, personalized feedback. It proposes a tag annotation workflow that converts student performance data into 34 binary tags and generates reports via GPT-4 using a structured prompt with sections for overview, analysis, strategies, and summary. The authors validate the approach with teacher surveys in Shanghai, showing generally high perceived usefulness and actionable insights, while highlighting clarity improvements needed. The work demonstrates a scalable path to integrate LLM-based feedback into adaptive learning systems, reducing teacher workload while preserving constructive, student-centered guidance.

Abstract

This study introduces a novel method that employs tag annotation coupled with the ChatGPT language model to analyze student learning behaviors and generate personalized feedback. Central to this approach is the conversion of complex student data into an extensive set of tags, which are then decoded through tailored prompts to deliver constructive feedback that encourages rather than discourages students. This methodology focuses on accurately feeding student data into large language models and crafting prompts that enhance the constructive nature of feedback. The effectiveness of this approach was validated through surveys conducted with over 20 mathematics teachers, who confirmed the reliability of the generated reports. This method can be seamlessly integrated into intelligent adaptive learning systems or provided as a tool to significantly reduce the workload of teachers, providing accurate and timely feedback to students. By transforming raw educational data into interpretable tags, this method supports the provision of efficient and timely personalized learning feedback that offers constructive suggestions tailored to individual learner needs.

A Study on Educational Data Analysis and Personalized Feedback Report Generation Based on Tags and ChatGPT

TL;DR

This paper addresses the challenge of turning rich educational data into timely, personalized feedback. It proposes a tag annotation workflow that converts student performance data into 34 binary tags and generates reports via GPT-4 using a structured prompt with sections for overview, analysis, strategies, and summary. The authors validate the approach with teacher surveys in Shanghai, showing generally high perceived usefulness and actionable insights, while highlighting clarity improvements needed. The work demonstrates a scalable path to integrate LLM-based feedback into adaptive learning systems, reducing teacher workload while preserving constructive, student-centered guidance.

Abstract

This study introduces a novel method that employs tag annotation coupled with the ChatGPT language model to analyze student learning behaviors and generate personalized feedback. Central to this approach is the conversion of complex student data into an extensive set of tags, which are then decoded through tailored prompts to deliver constructive feedback that encourages rather than discourages students. This methodology focuses on accurately feeding student data into large language models and crafting prompts that enhance the constructive nature of feedback. The effectiveness of this approach was validated through surveys conducted with over 20 mathematics teachers, who confirmed the reliability of the generated reports. This method can be seamlessly integrated into intelligent adaptive learning systems or provided as a tool to significantly reduce the workload of teachers, providing accurate and timely feedback to students. By transforming raw educational data into interpretable tags, this method supports the provision of efficient and timely personalized learning feedback that offers constructive suggestions tailored to individual learner needs.
Paper Structure (11 sections, 2 figures, 2 tables)

This paper contains 11 sections, 2 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Traditional Feedback Generation with LLMs in Education
  4. Effective Reporting in Educational Feedback
  5. Experiment and Data Analysis
  6. Experimental Procedure and Data Acquisition
  7. Data Processing and Tag Annotation
  8. Tag Parsing and Report Generation
  9. Evaluation
  10. Discussion and Implications
  11. Conclusion

Figures (2)

  • Figure 1: Adaptive learning system interface display.
  • Figure 2: Boxplot of questionnaire results across five dimensions.