The effect of prompt engineering-based structured AI-assisted feedback on pre-service physics teachers’ inquiry-based science teaching self-efficacy and feedback literacy
Educational Psychology, 2026 (SSCI, Scopus)
- Yayın Türü: Makale / Tam Makale
- Basım Tarihi: 2026
- Doi Numarası: 10.1080/01443410.2026.2680187
- Dergi Adı: Educational Psychology
- Derginin Tarandığı İndeksler: Social Sciences Citation Index (SSCI), Scopus, IBZ Online, Periodicals Index Online, Agricultural & Environmental Science Database, EBSCO Education Source, Education Abstracts, Educational research abstracts (ERA), ERIC (Education Resources Information Center), Psycinfo, Academic Search Ultimate (EBSCO), Social Science Premium Collection (ProQuest), Education Collection (ProQuest), Education Source Ultimate (EBSCO), Health Research Premium Collection (ProQuest), Sociology Source Ultimate (EBSCO)
- Anahtar Kelimeler: AI in Education Tool, Feedback Literacy, Inquiry-Based Science Teaching Self-Efficacy, Prompt Engineering, Teacher Education
- Hacettepe Üniversitesi Adresli: Evet
Özet
Although AI-assisted feedback has become increasingly prevalent in teacher education, empirical evidence on how such feedback assists inquiry-based science teaching self-efficacy and the role of feedback literacy in this process remains limited. This study examined the effects of prompt engineering-based structured AI-assisted feedback on pre-service physics teachers’ inquiry-based science teaching self-efficacy and feedback literacy. Grounded in Bandura’s self-efficacy theory and the feedback literacy framework proposed by Carless and Boud, the research employed a quasi-experimental pre-test post-test control group design. Data were collected from 80 pre-service physics teachers enrolled in a mechanics laboratory course. The experimental group received process-oriented, guiding, and ChatGPT-based personalised feedback that did not directly provide solutions, delivered through the Learning with AI about Physics (LEAP) platform and structured via prompt engineering, whereas the control group received routine instructor expertise feedback. Data were collected using validated scales, and semi-structured interviews were conducted with participants in the experimental group. The findings indicate that AI-assisted feedback led to statistically significant and moderate increases in inquiry-based science teaching self-efficacy and feedback literacy compared to the control group. The study concludes by recommending the integration of AI-assisted pedagogical feedback into teacher education within ethical and pedagogical principles.