LessonPlanner: Assisting Novice Teachers to Prepare Pedagogy-Driven Lesson Plans with Large Language Models

TL;DR

LessonPlanner leverages large language models to assist novice teachers in creating detailed, pedagogy-driven lesson plans, significantly improving quality and reducing workload through an interactive, adaptive system based on Gagne's nine events.

Contribution

This work introduces LessonPlanner, a novel LLM-based tool that supports novice teachers in constructing effective lesson plans aligned with educational theories.

Findings

LessonPlanner improves lesson plan quality.

It reduces teachers' workload.

It effectively suggests teaching strategies and resources.

Abstract

Preparing a lesson plan, e.g., a detailed road map with strategies and materials for instructing a 90-minute class, is beneficial yet challenging for novice teachers. Large language models (LLMs) can ease this process by generating adaptive content for lesson plans, which would otherwise require teachers to create from scratch or search existing resources. In this work, we first conduct a formative study with six novice teachers to understand their needs for support of preparing lesson plans with LLMs. Then, we develop LessonPlanner that assists users to interactively construct lesson plans with adaptive LLM-generated content based on Gagne's nine events. Our within-subjects study (N=12) shows that compared to the baseline ChatGPT interface, LessonPlanner can significantly improve the quality of outcome lesson plans and ease users' workload in the preparation process. Our expert interviews (N=6) further demonstrate LessonPlanner's usefulness in suggesting effective teaching strategies and meaningful educational resources. We discuss concerns on and design considerations for supporting teaching activities with LLMs.