RECIPE4U: Student-ChatGPT Interaction Dataset in EFL Writing Education
Jieun Han, Haneul Yoo, Junho Myung, Minsun Kim, Tak Yeon Lee, So-Yeon Ahn, Alice Oh
TL;DR
The paper tackles the scarcity of large-scale, real-world data on student–AI interactions in education, focusing on EFL writing. It introduces RECIPE4U, a semester-long dataset capturing 212 university students' dialogues with ChatGPT to revise essays, including 4330 utterances, 13-intent labels, self-rated satisfaction, and utterance-level essay edit histories. It establishes baselines for two task-oriented subtasks—intent detection and satisfaction estimation—using multilingual encoders and GPT variants, and analyzes student dialogue patterns, essay statistics, and edit behaviors to inform future LLM-enabled education. The findings reveal nuanced student perceptions of ChatGPT (as human-like AI, multilingual entity, and intelligent peer) and document how feedback is accepted or rejected, offering practical implications for instructional design, prompt engineering, and learning analytics. RECIPE4U is publicly available to support further research in educational AI and to guide the development of learning-support tools and instructor dashboards.
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/.