NIRVANA: A Comprehensive Dataset for Reproducing How Students Use Generative AI for Essay Writing

TL;DR

This paper introduces NIRVANA, a detailed dataset capturing university students' interactions with ChatGPT during essay writing, enabling analysis of AI's influence on student work and writing behaviors.

Contribution

The paper presents a new comprehensive dataset and a replay interface to systematically study student-AI interactions in educational writing tasks.

Findings

Identified four distinct student writing profiles based on AI interaction patterns.

Revealed variation in ChatGPT query frequency correlates with essay length and readability.

Developed a replay tool for systematic analysis of student-AI collaborative writing.

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.