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 guided by Gagné’s Nine Events of Instruction — a well-established instructional design theory. LessonPlanner structures the lesson plan as nine sections based on the nine events, and provides preset action buttons in each section to guide users to query an LLM for instructionally sound content. A within-subjects study (N=16) and expert interviews (N=12) show LessonPlanner can improve the quality of lesson plans and reduce workload compared to an LLM chatbot, while also offering insights into novice teachers’ perceptions and expert teachers’ reflections on LLM-assisted lesson planning.
Download
