Designing AI Tutors for Interest-Based Learning: Insights from Human Instructors

2026-02-27

AI Summary

Interest-Based Learning (IBL) has been shown to enhance learning outcomes, yet teachers face significant challenges in scaling personalized instruction that integrates individual students’ interests. This study addresses this gap by analyzing multimodal data—including instructional materials, dialogue transcripts, interviews, and questionnaires—from 14 real-world one-on-one online tutoring sessions. Grounded in educational theory and human-computer interaction principles, the research systematically uncovers, for the first time, the strategies and underlying motivations human tutors employ to weave students’ interests into instruction. From these insights, the study distills core IBL practice patterns and proposes actionable design principles for large language model–driven AI tutors. These contributions offer critical theoretical foundations and technical pathways toward scalable, personalized interest-based education.

Technology Category

• Machine Learning: Multimodal Learning
• Humans and AI: Learning Human Values and Preferences
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• User Modeling, Personalization and Recommendation: Practical large-scale studies of user experience
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling

Abstract

Interest-based learning (IBL) is a paradigm of instruction in which educational content is contextualized using learners'interests to enhance content relevance. IBL has been shown to result in improved learning outcomes. Unfortunately, high effort is needed for instructors to design and deliver IBL content for individual students. LLMs in the form of AI tutors may allow for IBL to scale across many students. Designing an AI tutor for IBL, however, first requires an understanding of how IBL is implemented in teaching scenarios. This paper presents a study that seeks to derive this understanding from an analysis of how human instructors design and deliver IBL content. We studied 14 one-to-one online tutoring sessions (28 participants) in which tutors designed and delivered a lesson tailored to a student's self-identified interest. Using lesson artifacts, tutoring transcripts, interviews, and questionnaires, findings include themes on how tutors integrate interests during instruction and why. Finally, actionable design implications are presented for LLM-powered AI tutors that aim to deliver IBL at scale.

Problem

• Interest-Based Learning
• AI Tutors
• Personalized Instruction
• Educational Scalability
• Human-AI Collaboration

Innovation

• interest-based learning
• AI tutor
• large language models
• instructional design
• personalized education