Conceptual Understanding in Fundamental and Mechanical Physics Among Pre-Service Physics Teachers of Surindra Rajabhat University: a Statistic and Machine Learning Analysis
Main Article Content
Abstract
A study of conceptual understanding in fundamental and mechanical physics of pre-service physics teachers (PPTs) is a fundamental aspect that can improve the points of misunderstanding among students, including critical thinking (CR) and computational thinking (CO) skills. In this work, we analyzed 110 physics exam items, encompassing fundamental concepts, significant principles, units of measurement, vectors and their properties, one-dimensional motion, Newton's laws of motion, projectile motion, circular motion, and simple harmonic motion. To evaluate conceptual knowledge and identify correlations with the total physics score, we employed a machine learning approach involving five algorithms: random forest, logistic regression, support vector machine, naive Bayes, and K-nearest neighbor. The following conclusions could be drawn regarding the conceptual understanding of PPTs. Overall, they still to develop knowledge of fundamental concepts, encompassing critical and computational thinking skills. The average combined score for all study subjects was 39.8%, indicating that their understanding was insufficient to be considered competitive for selection as specialized physics teachers in the civil service examination. We highlighted that GPA played a significant role in the mathematics subject in predicting the total score of the physics exam through the implementation of the random forest algorithm in ML. This algorithm achieved an accuracy of approximately 67.0%, surpassing the performance of other algorithms. Thus, the overall GPA, school size, and high school gender also influenced the overall scores. Our study highlighted the interconnectedness between the subject materials of fundamental and mechanical physics, revealing misconceptions that need to be addressed to enhance the performance of PPTs in competitive examinations, and provided the significance of calculation skills in influencing physics exam scores.
Article Details

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
References
Abdrakhmanov, R., Zhaxanova, A., Karatayeva, M., Zholaushievna Niyazova, G., Berkimbayev, K., & Tuimebayev, A. (2024). Development of a framework for predicting students' academic performance in STEM education using machine learning methods. International Journal of Advanced Computer Science and Applications, 15(1), 38–46. https://doi.org/10.14569/IJACSA.2024.0150105
Alamri, L. H., Almuslim, R. S., Alotibi, M. S., Alkadi, D. K., Ullah Khan, I. & Aslam, N. (2020). Predicting student academic performance using support vector machine and random forest. n Proceedings of the 2020 3rd International Conference on Education Technology Management (ICETM 2020), 100–107. https://doi.org/10.1145/3446590.3446607
Banda, H. J. & Nzabahimana, J. (2021). Effect of integrating physics education technology simulations on students’ conceptual understanding in physics: A review of literature. Physical Review Physics Education Research, 17(2), 023108. https://doi.org/10.1103/PhysRevPhysEducRes.17.023108
Capriconia, J. & Mufit, F. (2022). Analysis of Concept Understanding and Students’ Attitudes towards Learning Physics in Material of Straight Motion. Jurnal Penelitian Pendidikan IPA, 8(3), 1453–1461. https://doi.org/10.29303/JPPIPA.V8I3.1381
Kaltakci-Gurel, D., Eryilmaz, A. & McDermott, L. C. (2016). Identifying pre-service physics teachers’ misconceptions and conceptual difficulties about geometrical optics. European Journal of Physics, 37(4), 045705. https://doi.org/10.1088/0143-0807/37/4/045705
Liu, X. & Ardakani, S. P. (2022). A machine learning enabled affective E-learning system model. Education and Information Technologies, 27(7), 9913–9934. https://doi.org/10.1007/S10639-022-11010-X
Mameno, T., Wada, M., Nozaki, K., Takahashi, T., Tsujioka, Y., Akema, S., Hasegawa, D. & Ikebe, K. (2021). Predictive modeling for peri-implantitis by using machine learning techniques. Scientific Reports, 11(1), 11090. https://doi.org/10.1038/s41598-021-90642-4
Mills, S. (2016). Teaching and Learning Medication Calculations: A Grounded Theory of Conceptual Understanding. International Journal of Nursing Education Scholarship, 13(1), 1-9. https://doi.org/10.1515/IJNES-2015-0076
Nimy, E., Mosia, M. & Chibaya, C. (2023). Identifying At-Risk Students for Early Intervention—A Probabilistic Machine Learning Approach. Applied Sciences, 13(6), 3869. https://doi.org/10.3390/APP13063869
Sagala, R., Umam, R., Thahir, A., Saregar, A. & Wardani, I. (2019). The effectiveness of stem-based on gender differences: The impact of physics concept understanding. European Journal of Educational Research, 8(3), 753–761. https://doi.org/10.12973/EU-JER.8.3.753
Sarapak, C., Kong-In, P., Jindasri, P., Kakkaew, V., Wattanakornsiri, A., Yoomark, J., Sumrandee, C., Sreejivungsa, K., Malingam, N., Krongsuk, S., & Lunnoo, T. (2025). Instrument design and validation for enhancing instructional design using the TPACK framework: A study in Surin Province. Journal of Innovation, Advancement, and Methodology in STEM Education (J-IAMSTEM), 2(1), 10–24. https://so13.tci-thaijo.org/index.php/j_iamstem
Sathe, M. T. & Adamuthe, A. C. (2021). Comparative study of supervised algorithms for prediction of students’ performance. International Journal of Modern Education and Computer Science, 13(1), 1-21. https://doi.org/10.5815/IJMECS.2021.01.01
Su, Y. S., Lin, Y. D & Liu, T. Q. (2022). Applying machine learning technologies to explore students’ learning features and performance prediction. Frontiers in Neuroscience, 16, 1018005. https://doi.org/10.3389/FNINS.2022.1018005
Yana, A. U., Antasari, L. & Kurniawan, B. R. (2019). nalisis pemahaman konsep gelombang mekanik melalui aplikasi online Quizizz. Jurnal Pendidikan Sains Indonesia, 7(2), 143–152. https://doi.org/10.24815/JPSI.V7I2.14284
Zhai, X., Yin, Y., Pellegrino, J. W., Haudek, K. C. & Shi, L. (2020). Applying machine learning in science assessment: a systematic review. Studies in Science Education, 56(1), 111–151. https://doi.org/10.1080/03057267.2020.1735757
Zulfa, I., Kusairi, S., Latifah, E. & Jauhariyah, M. N. R. (2019). Analysis of student’s conceptual understanding on the work and energy of online hybrid learning. Journal of Physics: Conference Series, 1171(1), 012045. https://doi.org/10.1088/1742-6596/1171/1/012045