Comparing Expert-Written, AI-Generated, and Interactive AI Dialogue for Heat and Temperature Conceptual Understanding

Synthesis: Akdoğan (2025) empirically investigates whether Generative AI improves students' conceptual understanding of heat and temperature. Using a quasi-experimental Solomon Four-Group design with 413 10th-grade students in Ankara, Türkiye, the thesis compared three interventions targeting heat/temperature misconceptions: an expert-written conceptual change text (CCT), an AI-generated CCT, and an interactive AI dialogue with ChatGPT. Findings reveal that both CCT interventions — expert and AI-generated — were equally and significantly more effective at reducing misconceptions than the interactive AI dialogue, which offered no significant advantage over the control group. Intervention benefits were almost exclusively limited to high-achieving students; personal epistemologies (about justification and changeability of knowledge) and metacognitive awareness of global reading strategies significantly moderated results.

Key Findings

• Conceptual change text (CCT) beats interactive AI dialogue — the reverse of Corbett & Tangen (2026). Both expert-written and AI-generated conceptual change texts were equally and significantly more effective at reducing misconceptions than interactive ChatGPT dialogue, which showed no significant advantage over control. This contrasts with the personalised-dialogue advantage found in Corbett & Tangen (2026), likely due to differences in dialogue design (prompted vs. personalised) and domain.
• Expert and AI-generated CCT are comparable. An AI-generated conceptual change text performed as well as one written by an expert — suggesting AI can produce effective refutation/conceptual-change content.
• Benefits concentrated in high-achieving students. Intervention gains were almost exclusively limited to high achievers, pointing to a equity concern for AI-mediated conceptual-change instruction.
• Individual differences moderate outcomes. Students' personal epistemologies (justification and changeability of knowledge) and metacognitive awareness of global reading strategies significantly moderated the results — consistent with the misconception and Metacognition literature.
• GAI's current pedagogical value is as a content generator, not an interactive tutor. The author concludes GAI's value in this context lies in producing structured-prompt content, not yet in functioning as an interactive tutor for conceptual change.

Implications for AI in Education

The thesis adds a critical empirical counterpoint to the AI-dialogue-for-misconception-correction literature: in this large K 12 science context, well-structured conceptual-change texts (expert or AI-generated) outperformed freeform interactive AI dialogue. For practice, it suggests that for science misconception correction, AI is most valuable as a scalable generator of effective refutation texts, and that intervention design must attend to learner achievement, epistemology, and Metacognition. It connects to the knowledge base's conceptual change, Misconceptions, Refutation Text, and Generative AI concepts.

Connected Concepts

• Refutation Text
• Misconceptions
• STEM Education
• Physics Education
• Metacognition
• Equity In AI Education
• Generative AI

Connected Articles

• AI Tutors Vs Tenacious Myths Personalised Dialogue 2026 — Personalised AI dialogue vs. textbook refutation for belief correction
• Llms Misconception Collaborative Learning Healthcare 2026 — LLM-generated misconceptions for collaborative learning

Citation

Akdoğan, S. (2025). Comparing the effectiveness of expert-written text, AI-generated text, and interactive AI dialogues on students' conceptual understanding of heat and temperature (Doctoral dissertation, Middle East Technical University).