Date
Publisher
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.
Study at a glance
- Question: How do undergraduate students use ChatGPT for self-directed learning, and what influences their continued engagement over time?
- Setting and data: 10,536 naturalistic messages donated by 36 undergraduate students over a year.
- Method: Qualitative coding and automated text annotation combined with statistical modeling (sequential mixed-methods pipeline).
Why it matters
Understanding how students really use ChatGPT requires uncovering how they integrate the tool into everyday self-directed learning and how interactions link to sustained engagement.
Key findings
- Among 36 undergraduate students, system-issued apologies were the strongest predictor of increased ChatGPT engagement, outweighing whether tasks were successfully completed.
- Using ChatGPT for structured tasks, such as coding, theory application, and multiple-choice questions, predicted continued use by students.
- Interaction strain, including prompt revisions, user frustration, and follow-up clarifications, predicted that students would disengage from and abandon the tool.
Summary drafted with AI from the paper’s abstract and may contain errors. See the full paper for details.
What is the application?
Who is the user?
Who age?
Why use AI?
Study design
