Date
Publisher
arXiv
This exploratory case study investigated two contrasting pedagogical
approaches for LCA-assisted programming with five novice high school students
preparing for a WeChat Mini Program competition. In Phase 1, students used LCAs
to generate code from abstract specifications (From-Scratch approach),
achieving only 20% MVP completion. In Phase 2, students adapted existing
Minimal Functional Units (MFUs), small, functional code examples, using LCAs,
achieving 100% MVP completion. Analysis revealed that the MFU-based approach
succeeded by aligning with LCA strengths in pattern modification rather than de
novo generation, while providing cognitive scaffolds that enabled students to
navigate complex development tasks. The study introduces a dual-scaffolding
model combining technical support (MFUs) with pedagogical guidance (structured
prompting strategies), demonstrating that effective LCA integration depends
less on AI capabilities than on instructional design. These findings offer
practical guidance for educators seeking to transform AI tools from sources of
frustration into productive learning partners in programming education.
Study at a glance
- Question: How do different teaching approaches using AI tools support high school students learning to code?
- Setting and data: Five novice high school students preparing for a WeChat Mini Program competition.
- Method: Case study comparing two teaching approaches across two phases (exploratory case study)
Why it matters
In programming education, AI tools can be sources of frustration rather than productive learning partners. Educators need pedagogical approaches that support novice high school students in AI-assisted programming.
Key findings
- In a programming competition with five novice high school students, using AI to modify existing code achieved 100% completion versus 20% from scratch.
- The AI tool was more effective at modifying existing code patterns than at generating brand-new code from abstract student instructions.
- Successful AI integration depended less on the tool's technical capabilities and more on instructional design and structured prompting guidance.
Summary drafted with AI from the paper’s abstract and may contain errors. See the full paper for details.
What is the application?
Who is the user?
Who age?
Why use AI?
Study design
