NIRVANA: A Comprehensive Dataset for Reproducing How Students Use Generative AI for Essay Writing
2026-04-08 • Human-Computer Interaction
Human-Computer Interaction
AI summaryⓘ
The authors studied how university students use ChatGPT to help write essays by collecting detailed data on their writing and interactions with the AI. They created a dataset called NIRVANA that tracks keystrokes, AI conversations, and copied text to fully capture the writing process. Their analysis showed different ways students use AI help and grouped them into four types based on how much they relied on and revised AI content. They also built a tool that lets others replay the writing process to better understand how students and AI work together.
AI writing assistantsgenerative AIChatGPTkeystroke loggingwriting process analysiseducational technologystudent writing behaviordata replay interfaceessay writinghuman-AI interaction
Authors
Andrew Jelson, Daniel Manesh, Sangwook Lee, Alice Jang, Daniel Dunlap, Tamara Maddox, Young-Ho Kim, Sang Won Lee
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.