Micro-level AI Feedback Features and Student Responses in Consecutive LLM Tutoring Interactions
2026-07-09 • Human-Computer Interaction
Human-Computer Interaction
AI summaryⓘ
The authors studied how small features in AI feedback affect a student's next learning step during conversations with an AI tutor. They looked at detailed explanations, emotional tone, and how long the AI's responses were. Their analysis showed that detailed, concrete explanations helped students understand better and feel less confused next time. Emotional language didn’t change understanding, and longer responses tended to make understanding worse. This suggests clear, specific feedback is important for quick learning in AI tutoring.
AI feedbackmicro-level featuresconcrete elaborationaffective languageresponse lengthstudent confusionunderstandinguser-AI interactionStudyChat datasetGeneralized Estimating Equations
Authors
Shayla Sharmin, Mohammad Fahim Abrar, Roghayeh Leila Barmaki
Abstract
AI-assisted feedback research has shown that micro-level feedback features, such as concrete elaboration, affective language, and response length, are associated with learning outcomes. Existing studies have primarily examined these features using session- or task-level measures. We examine how feedback provided in one user-AI interaction is associated with student confusion and understanding in the immediately following interaction in a naturalistic tutoring setting. We focus on three micro-level features of AI feedback: concrete elaboration (analogies, comparison-based explanations, or worked examples), affective language (encouragement, empathy, or apology), and response length. We analyzed 16,851 conversational user-AI interactions from the StudyChat dataset, a naturalistic record of student interactions with an LLM tutor in an undergraduate AI course, and identified 1,718 cases in which students expressed confusion and continued to a subsequent interaction. Using chi-square tests and Generalized Estimating Equations (GEE), we found that concrete elaboration was associated with higher understanding and lower re-confusion in the student's next interaction. Empathetic language showed no significant association with either outcome, while longer responses were independently associated with lower understanding. These findings highlight the value of examining feedback across consecutive user-AI interactions and suggest that concrete elaboration may play an important role in supporting immediate student understanding.