# How Students (Really) Use ChatGPT: Uncovering Experiences Among Undergraduate Students

arXiv: https://arxiv.org/abs/2505.24126 · HTML: https://mlsanity.com/paper/2505.24126/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 May 2025.

## Built on by (most cited first, 5 of 5)

- [TutorBench: A Benchmark To Assess Tutoring Capabilities Of Large Language Models](https://mlsanity.com/paper/2510.02663/) (2025)
- [Priming, Path-dependence, and Plasticity: Understanding the molding of user-LLM interaction and its implications from (many) chat logs in the wild](https://mlsanity.com/paper/2605.05767/) (2026)
- [Rethinking Scaffolding in LLM Tutors: The Interactional Mismatch Between Benchmarks and Real-World Deployments](https://mlsanity.com/paper/2606.15766/) (2026)
- [Thematic and Task-Based Categorization of K-12 GenAI Usages with Hierarchical Topic Modeling](https://mlsanity.com/paper/2508.09997/) (2025)
- ["How Do I ...?": Procedural Questions Predominate Student-LLM Chatbot Conversations](https://mlsanity.com/paper/2602.18372/) (2026)

## Abstract (arXiv)

We examine how undergraduate students integrate ChatGPT into everyday self-directed learning, analyzing 10,536 naturalistic messages donated by 36 students over a year. A sequential mixed-methods pipeline pairs iterative qualitative coding with zero-shot language-model annotation validated against human labels (kappa = 0.75-0.91). It yields a five-category taxonomy: Information Seeking, Content Generation, Language Use, Student-ChatGPT Interaction, and ChatGPT Response Behavior. Time-lagged linear regression and Cox proportional-hazards models link these categories to sustained engagement. Three findings stand out. First, structured tasks (theory application, code writing, job-application content, multiple-choice questions) predict continued use; ChatGPT becomes incorporated into academic rhythms when gratifications are reliably fulfilled. Second, system-issued "apologies" are the strongest positive predictor of increased engagement, outweighing every task-completion predictor. We name this mechanism "repair gratification": the reward of a breakdown acknowledged and repaired rather than a task simply completed. Third, interactional strain--prompt revision, frustration, follow-up clarification--predicts disengagement. When managing the system falls on the user without system accountability, students abandon the tool. We interpret these results through Self-Directed Learning, Uses and Gratifications Theory, and Expectancy Violations Theory, mapping predictors onto positive/negative violations and confirmations. We close with design recommendations for graduated repair patterns, mode-aware interaction, and verification affordances, and outline a participatory AI-literacy agenda for higher education.