Problem
Research questions and friction points this paper is trying to address.
generative AI
student writing
AI writing assistants
educational technology
human-AI interaction
NIRVANA: A Comprehensive Dataset for Reproducing How Students Use Generative AI for Essay Writing
🤖 AI Summary
This study addresses the lack of systematic understanding regarding how students employ generative AI in authentic writing tasks. The authors constructed a fine-grained dataset comprising 77 undergraduate students’ use of ChatGPT to compose analytical essays, capturing keystroke logs, full dialogue histories, and copied content to enable the first comprehensive tracing of human–AI collaborative writing processes. Through textual comparison, process replay, and visual analytics, they identified four distinct writer roles: Lead Authors, Collaborators, Drafters, and Vibe Writers. The analysis further reveals associations between these roles and essay characteristics such as length and readability, offering empirical grounding for understanding the real-world impact of generative AI on educational writing practices.
📝 Abstract
With the rapid adoption of AI writing assistants in education, educators and researchers need empirical evidence to understand the impact on student writing and inform effective pedagogical design. Despite widespread use, we lack systematic understanding of how students engage with these tools during authentic writing tasks: when they seek assistance, what they ask, and how they incorporate AI-generated content into their essays. This gap limits evidence-based policy development and rigorous evaluation of generative AI's learning effects. To address this gap, we introduce NIRVANA, a dataset capturing how university students use generative AI while writing an analytical essay. The dataset includes 77 students who completed an essay task with access to ChatGPT, recording keystroke-level writing behavior, full ChatGPT conversation histories, and all text copied from ChatGPT, enabling a complete reconstruction of the writing process and revealing how AI assistance shapes student work. Our analysis identifies key behavioral patterns, including variation in ChatGPT query frequency and its relationship to essay characteristics such as length and readability. We identify four writing profiles based on students' contribution and revision patterns: Lead Authors, Collaborators, Drafters, and Vibe Writers. To support deeper investigation, we developed a replay interface that reconstructs the writing process; qualitative analysis of sampled replays demonstrates how this tool enables systematic examination of student-AI interactions.
Innovation
Methods, ideas, or system contributions that make the work stand out.
generative AI
writing process
keystroke logging
human-AI collaboration
educational dataset
🔎 Similar Papers
No similar papers found.
