Search and Filter

Designing AI Tutors For Interest-Based Learning: Insights From Human Instructors

Date

AI Overview

Why it matters

Personalizing lessons to students' interests improves learning outcomes, but manually designing interest-based instruction requires significant instructor effort. Understanding how human tutors integrate interests can guide the design of AI tutors to scale personalized learning effectively.

Study at a glance
  • Question: How do human tutors integrate students' interests into instruction, and how do participants perceive it?
  • Setting and data: Fourteen online Zoom tutoring pairs (28 adult participants: 14 tutors and 14 students).
  • Method: Qualitative analysis of lesson plans, tutoring session transcripts, and post-session interviews.
Key findings
  • Tutors used student interests primarily to build rapport (12 of 14 sessions), introduce unfamiliar concepts (12 sessions), and hand over dialogue to students (9 sessions).
  • Tutors most often integrated interests through analogical bridges (38 of 71 instances), followed by illustrative examples (23 instances) and contextualizing scenarios (10 instances).
  • Students reported that integrating their interests made lessons feel more casual and engaging, while tutors found it encouraged conversation but sometimes made coherent transitions difficult.

Summary drafted with AI from the full paper and may contain errors. See the full paper for details.

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.