RECIPE4U: Student-ChatGPT Interaction Dataset in EFL Writing Education

TL;DR

RECIPE4U is a comprehensive dataset capturing student-ChatGPT interactions in EFL writing courses, enabling analysis of dialogue patterns, intent detection, and satisfaction estimation to improve AI-assisted education.

Contribution

This paper introduces RECIPE4U, a novel large-scale dataset of student-AI interactions in educational settings, with annotated intents and satisfaction labels, facilitating research on AI in language learning.

Findings

Analyzed student-ChatGPT interaction patterns and dialogue data.

Established baseline results for intent detection and satisfaction estimation.

Demonstrated potential applications for enhancing AI integration in education.

Abstract

The integration of generative AI in education is expanding, yet empirical analyses of large-scale and real-world interactions between students and AI systems still remain limited. Addressing this gap, we present RECIPE4U (RECIPE for University), a dataset sourced from a semester-long experiment with 212 college students in English as Foreign Language (EFL) writing courses. During the study, students engaged in dialogues with ChatGPT to revise their essays. RECIPE4U includes comprehensive records of these interactions, including conversation logs, students' intent, students' self-rated satisfaction, and students' essay edit histories. In particular, we annotate the students' utterances in RECIPE4U with 13 intention labels based on our coding schemes. We establish baseline results for two subtasks in task-oriented dialogue systems within educational contexts: intent detection and satisfaction estimation. As a foundational step, we explore student-ChatGPT interaction patterns through RECIPE4U and analyze them by focusing on students' dialogue, essay data statistics, and students' essay edits. We further illustrate potential applications of RECIPE4U dataset for enhancing the incorporation of LLMs in educational frameworks. RECIPE4U is publicly available at https://zeunie.github.io/RECIPE4U/.