Think, Retrieve, Master: An AI-Assisted Intervention for Thermodynamics Conceptual Mastery in Physics 2
Authors
Master Teacher II, Schools Division Office of Antipolo DLC I-A Antipolo City Senior High School (Philippines)
Article Information
DOI: 10.47772/IJRISS.2026.1026EDU0562
Subject Category: Physical Education
Volume/Issue: 10/26 | Page No: 7626-7639
Publication Timeline
Submitted: 2026-08-27
Accepted: 2026-09-01
Published: 2026-09-10
Abstract
This study examined changes in thermodynamics conceptual mastery following the implementation of the Artificial Intelligence (AI)-Assisted Retrieval Model (AI-ARM) among Grade 11 learners in Physics 2. Specifically, it examined learners’ conceptual understanding, quantitative reasoning, and application of thermodynamic principles before and after the intervention and documented learners’ perceptions of the learning experience. The study employed a mixed-method explanatory sequential design, with a one-group pretest–posttest quantitative component and thematic analysis of qualitative reflections. Nineteen (19) purposively selected learners participated in a four-week intervention conducted during homeroom sessions, integrating structured retrieval practice and AI-assisted explanatory feedback. Data were collected using a 40-item Thermodynamics Conceptual Mastery Test, reflection logs, and a perception survey. Mean performance increased from 24.58 (SD = 5.52) in the pretest to 33.16 (SD = 2.21) in the posttest, a mean increase of 8.58 points. A paired-samples t-test indicated a statistically significant pretest–posttest difference, t(18) = 6.67, p < .001. For the paired design, Cohen’s dz was estimated as t/√n = 1.53, indicating a large standardized mean difference; the 95% confidence interval for the mean difference, based on the reported t statistic, was approximately 5.88 to 11.28 points. Qualitative findings highlighted simplification of complex concepts, conceptual clarity, guided error correction, increased confidence, and improved application. Because the study had no control or comparison group and used a small purposive sample, the observed gains cannot be interpreted as definitive evidence that AI-ARM alone caused the improvement. Repeated testing, normal classroom learning, learner motivation, and other concurrent learning experiences may also have contributed. The findings therefore provide preliminary classroom-based evidence that AI-assisted retrieval is a promising remediation approach that warrants further evaluation using controlled or comparison-group designs.
Keywords
Artificial intelligence (AI), AI-assisted learning, retrieval practice, thermodynamics, conceptual mastery
Downloads
References
1. Kelley, T. R., & Knowles, J. G. (2021). A conceptual framework for integrated STEM education and sustainability thinking. Journal of STEM Education Research, 4(2), 123–139. https://doi.org/10.1007/s41979-020-00041-4 [Google Scholar] [Crossref]
2. Morales, M. P. E., & Santos, J. M. (2022). Classroom action research as a driver of instructional innovation in secondary science education. International Journal of Educational Research Open, 3, 100143. https://doi.org/10.1016/j.ijedro.2022.100143 [Google Scholar] [Crossref]
3. Singh, C., & Marshman, E. (2021). Student difficulties in thermodynamics and implications for instruction. Physical Review Physics Education Research, 17(1), 010110. https://doi.org/10.1103/PhysRevPhysEducRes.17.010110 [Google Scholar] [Crossref]
4. Wisniewski, B., Zierer, K., & Hattie, J. (2021). The power of feedback revisited: A meta-analysis of educational feedback research. Frontiers in Psychology, 12, 678541. https://doi.org/10.3389/fpsyg.2021.678541 [Google Scholar] [Crossref]
5. Yang, C., Luo, L., Vadillo, M. A., Yu, R., & Shanks, D. R. (2021). Testing enhances learning: A meta-analysis of the retrieval practice effect. Psychological Bulletin, 147(4), 399–435. https://doi.org/10.1037/bul0000306 [Google Scholar] [Crossref]
6. Zawacki-Richter, O., Bond, M., Marin, V. I., & Gouverneur, F. (2022). Systematic review of research on artificial intelligence applications in higher education and implications for secondary education. Computers and Education: Artificial Intelligence, 3, 100054. https://doi.org/10.1016/j.caeai.2022.10005 [Google Scholar] [Crossref]
Metrics
Views & Downloads
Similar Articles
- Combined and Isolated Effect of SAQ Training and Resistance Training on Agility and Flexibility among Badminton Players
- Importance of Ashtanga Yoga in Physical Education and Mental Health
- Navigating the Path of Exceptional Parenting: An Exploration of Experiences among Parents of Para-Athletes
- Effects of a 12-Week Football Intervention on Mental Health and Psychological Resilience in Secondary School Students
- Academic Achievement, Enthusiasm and Attitude of High School Students Regarding Quizizz as an Educational Gamification Tool for Physics