NIRVANA: A Comprehensive Dataset for Reproducing How Students Use Generative AI for Essay Writing
This addresses the need for empirical evidence to inform educational policy and pedagogy regarding AI writing assistants, though it is incremental as it provides a dataset rather than a new method.
The researchers tackled the lack of systematic understanding of how students use generative AI for essay writing by introducing the NIRVANA dataset, which captures keystroke-level behavior and ChatGPT interactions from 77 university students, revealing patterns like four distinct writing profiles and relationships between query frequency and essay characteristics.
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.