Turkish-language prompts produced poorer EDBL alignment than English prompts, revealing a linguistic equity limitation of AI lesson-planning tools¶

Claim · All claims
Evidence · 1 study · design r2 · q1
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person · recheck by 2029: tool and model accuracy changes quickly

Subclaims¶

q1 i? Pilot testing showed both platforms failed to adequately interpret the EDBL framework when prompted in Turkish, while English prompts produced more pedagogically coherent outputs. → Karaismailoglu 2026

Evidence¶

Karaismailoglu 2026¶

Karaismailoglu, F., Surmeli, H., & Yildirim, M. (2026). Suitability of Artificial Intelligence Supported Lesson Plans from the Perspective of Science Education Experts. Journal of Science Education and Technology. https://doi.org/10.1007/s10956-026-10342-4

q1 · i? · design · r2

Pilot observation during prompt development, reported in the Methodology. Both platforms prompted in Turkish produced plans that "did not reflect the iterative, process-oriented nature of EDBL," so the final prompt was written in English. No systematic test was reported.

"pilot testing revealed that both AI platforms (ChatGPT-4 and Teacher's Buddy) failed to adequately interpret the EDBL framework when prompted in Turkish. The generated lesson plans did not reflect the iterative, process-oriented nature of EDBL."

Discussion¶

Related Claims¶

• The general-purpose platform scored higher in early EDBL stages while the education-focused platform scored higher in feedback-intensive iterative stages — related
• Academic integrity, professional development, and equity concerns about AI span all surveyed units, though interpreted differently — related
• Educators use AI tools mainly for personalized learning and language support and frequently use generative AI for lesson planning — related
• AI in adult education risks reinforcing existing inequalities via the digital divide, particularly for rural, low-income, and marginalized learners — related
• Both AI platforms received their lowest expert ratings in engineering skills, indicating a shared limitation in supporting iterative design competencies — related
• Generic AI tools can undermine curriculum coherence and pedagogical goals, producing low-quality artifacts that do not match district beliefs — related
• Feedback prompted with ELL status narrows to surface-level grammar and mechanics corrections, assuming limited language competency rather than addressing argument and reasoning — related