Is this project an undergraduate, graduate, or faculty project?
Undergraduate
Project Type
group
Campus
Daytona Beach
Authors' Class Standing
Beata Blood, Sophomore Maissane Aik Zoey Zaldivar
Lead Presenter's Name
Beata Blood
Lead Presenter's College
DB College of Engineering
Faculty Mentor Name
Dr. Emily Dux Speltz
Abstract
As generative AI tools like ChatGPT become more common in higher education, writing instructors face the challenge of guiding students toward effective and ethical use, particularly in asynchronous environments where immediate feedback is limited. This presentation reports on an exploratory study that addresses this challenge by shifting attention from AI’s outputs to students’ moment-by-moment writing processes. Grounded in applied linguistics approaches to writing research and process-tracing methods, the project employed case studies with both expert and novice users of GenAI. Expert participants, including academics and industry professionals, completed writing tasks while integrating AI into their workflows. Their sessions were recorded with a process-tracing tool and followed by stimulated recall interviews to elicit strategies. Parallel observations with student participants highlighted differences between expert-informed practices and the more fragmented ways students tend to engage with AI tools. Our analysis focused on when and how writers query GenAI, evaluate responses, and incorporate them into texts. From this, we developed a model of effective AI-assisted writing behavior. This model is being used to inform the design of a predictive system that provides process-focused feedback: rather than asking GenAI to generate advice, the system classifies student writing behaviors via supervised machine learning and delivers guidance aligned with expert strategies. The presentation will introduce the rationale for a process-oriented approach, share qualitative findings from expert and student case studies, and outline early development of the feedback system. Attendees will gain insight into how this research can inform pedagogy, assessment, and technology design for AI-supported writing instruction.
Did this research project receive funding support (Spark, SURF, Research Abroad, Student Internal Grants, Collaborative, Climbing, or Ignite Grants) from the Office of Undergraduate Research?
No
Included in
Artificial Intelligence and Robotics Commons, Educational Technology Commons, Rhetoric and Composition Commons
Designing Process-focused Feedback for College Writers Using GenAI
As generative AI tools like ChatGPT become more common in higher education, writing instructors face the challenge of guiding students toward effective and ethical use, particularly in asynchronous environments where immediate feedback is limited. This presentation reports on an exploratory study that addresses this challenge by shifting attention from AI’s outputs to students’ moment-by-moment writing processes. Grounded in applied linguistics approaches to writing research and process-tracing methods, the project employed case studies with both expert and novice users of GenAI. Expert participants, including academics and industry professionals, completed writing tasks while integrating AI into their workflows. Their sessions were recorded with a process-tracing tool and followed by stimulated recall interviews to elicit strategies. Parallel observations with student participants highlighted differences between expert-informed practices and the more fragmented ways students tend to engage with AI tools. Our analysis focused on when and how writers query GenAI, evaluate responses, and incorporate them into texts. From this, we developed a model of effective AI-assisted writing behavior. This model is being used to inform the design of a predictive system that provides process-focused feedback: rather than asking GenAI to generate advice, the system classifies student writing behaviors via supervised machine learning and delivers guidance aligned with expert strategies. The presentation will introduce the rationale for a process-oriented approach, share qualitative findings from expert and student case studies, and outline early development of the feedback system. Attendees will gain insight into how this research can inform pedagogy, assessment, and technology design for AI-supported writing instruction.