An Empirical Study to Understand How Students Use ChatGPT for Writing Essays

要旨

As large language models (LLMs) become widespread, students increasingly turn to systems like ChatGPT for writing tasks. Educators worry that this reliance may reduce critical engagement with writing and hinder students' learning processes. Although datasets exist on students’ use of LLMs for writing, how they functionally use ChatGPT in detail---and how this usage shapes their writing and perceptions---remains underexplored. We conducted an online study (n=77) in which students wrote an essay using an in-house ChatGPT we developed to capture their queries. Through qualitative analysis, we identified the types of assistance students sought and presented patterns of use, ranging from asking for opinions on a topic to delegating the entire writing task to ChatGPT. We also found that students' writing self-efficacy influenced their querying patterns and that levels of ownership and creativity varied depending on how they used ChatGPT. This study contributes empirical data to ongoing discussions about how writing education should incorporate or regulate LLM-powered tools.

著者
Andrew Jelson
Virginia Tech, Blacksburg, Virginia, United States
Daniel Manesh
Virginia Tech, Blacksburg, Virginia, United States
Alice Jang
Virginia Tech, Blacksburg, Virginia, United States
Daniel Dunlap
Virginia Tech, Blacksburg, Virginia, United States
Young-Ho Kim
NAVER AI Lab, Seongnam, Korea, Republic of
Sang Won Lee
Virginia Tech, Blacksburg, Virginia, United States

会議: CHI 2026

ACM CHI Conference on Human Factors in Computing Systems

セッション: Learning, Training, and Self-Development with AI

P1 - Room 125
7 件の発表
2026-04-13 20:15:00
2026-04-13 21:45:00