Topics and trends in physics teaching using artificial intelligence

Authors

  • Erick Ghuron Universidade de São Paulo
  • Daniel Trugillo Martins Fontes Universidade de São Paulo. Programa de Pós-Graduação Interunidades em Ensino de Ciências
  • André Machado Rodrigues Universidade de São Paulo. Instituto de Física

Keywords:

Machine learning, Information and communication technology, Quantitative analysis, Literature review

Abstract

This study investigates the application of machine learning, specifically using the Latent Dirichlet Allocation algorithm, to identify topics and trends in academic journals on Physics education in the Latin America context. The journals analyzed were the Revista Brasileira de Ensino de Física (RBEF) and the Revista de Enseñanza de la Física (REF), covering the period from 2001 to 2022. A total of 1664 articles from RBEF and 885 from REF were collected, representing 79% and 85% of the articles published in these periods, respectively. The results indicated dominant topics in each journal and their respective trends over time. For instance, RBEF showed a decline in topics related to Physics Education and an increase in publications on General Physics. In contrast, REF displayed a predominance of topics related to Teaching, with a significant rise in publications about Virtual Laboratory and Teaching. These findings provide valuable insights into the evolution of research themes in Physics education in the Brazilian and Argentine contexts and the potential of using machine learning in Physics education research.

References

Bird, S. (2016). Natural language processing with python. O’Reilly Media.

Blei, D. M., Ng, A. Y. & Jordan, M. I. (2003). Latent Dirichlet Allocation. J. Mach. Learn. Res., 3, 993–1022.

Carter, L. (2008). Sociocultural influences on science education: innovation for contemporary times. Science Education, 92(1), 165-181. DOI: 10.1002/sce.20228

Chen, X., Zou, D., Cheng, G. & Xie, H. (2020). Detecting latent topics and trends in educational technologies over four decades using structural topic modeling: A retrospective of all volumes of Computers & Education. Computers & Education, 151, 103855. DOI: 10.1016/j.compedu.2020.103855

Chollet, F. (2018). Deep learning with Python. Manning Publications.

Fontes, D. T. M. y Rodrigues, A. M. (2022). Tendencias de investigación en la enseñanza de la física en revistas académicas iberoamericanas. Revista De Enseñanza De La Física, 34(2), 33–45. DOI: 10.55767/2451.6007.v34.n2.39481

Goulart, B. N. K., Pastorio, D. P. e Vidmar, M. P. (2023). O papel do professor diante das tecnologias digitais de informação e comunicação no contexto do ensino remoto emergencial de Física e Ciências. Revista De Enseñanza De La Física, 35(1), 17–26. DOI: 10.55767/2451.6007.v35.n1.41387

Mitchell, R. E. (2018). Web scraping with Python: Collecting more data from the modern web (Second edition). O’Reilly Media.

Mitchell, T. M. (1997). Machine Learning. McGraw-Hill.

Odden, T. O. B., Marin, A. & Caballero, M. D. (2020). Thematic analysis of 18 years of physics education research conference proceedings using natural language processing. Physical Review Physics Education Research, 16(1), 010142. DOI: 10.1103/PhysRevPhysEducRes.16.010142

Odden, T. O. B., Marin, A. & Rudolph, J. L. (2021). How has Science Education changed over the last 100 years? An analysis using natural language processing. Science Education, 105(4), 653–680. DOI: 10.1002/sce.21623

Röder, M., Both, A. & Hinneburg, A. (2015). Exploring the Space of Topic Coherence Measures. Proceedings of the Eighth ACM International Conference on Web Search and Data Mining, 399–408. DOI: 10.1145/2684822.2685324

Syed, S. & Spruit, M. (2017). Full-Text or Abstract? Examining Topic Coherence Scores Using Latent Dirichlet Allocation. 2017 IEEE International Conference on Data Science and Advanced Analytics (DSAA), 165–174. DOI: 10.1109/DSAA.2017.61

Downloads

Published

2023-12-01

How to Cite

Topics and trends in physics teaching using artificial intelligence. (2023). Journal of Physics Teaching, 35, 167-173. https://revistas.psi.unc.edu.ar/index.php/revistaEF/article/view/43304