Classificação Automática de Movimentos Pedagógicos como Apoio à Análise e à Avaliação da Prática Docente: Um Estudo com a Base TalkMoves
Resumo
A avaliação sistemática da prática docente por meio da observação de aulas depende de avaliadores treinados, o que limita sua aplicação em larga escala. Este trabalho investiga em que medida técnicas clássicas de aprendizado de máquina podem apoiar a identificação automática de movimentos pedagógicos, entendidos como ações discursivas empregadas para conduzir a participação e o raciocínio em sala de aula. Foram utilizadas transcrições em inglês de aulas de matemática da base TalkMoves. Diferentes algoritmos de classificação e estratégias de combinação de modelos foram comparados a partir de uma mesma representação textual. O melhor modelo individual alcançou aproximadamente 65% de acurácia, enquanto a melhor combinação obteve 65,5% de acurácia e 65,2% de F1-score. Os resultados indicam que essas técnicas podem apoiar a triagem de trechos e a elaboração de feedback formativo, mas não apresentam desempenho suficiente para substituir a avaliação humana ou produzir julgamentos autônomos sobre a prática docente. O estudo oferece um baseline reprodutível e de baixo custo para futuras pesquisas sobre a análise automatizada do discurso em sala de aula.
Palavras-chave:
Análise da prática docente, avaliação docente, discurso de sala de aula, inteligência artificial na educação, aprendizado de máquina, TalkMoves
Referências
Alic, S., Demszky, D., Mancenido, Z., Liu, J., Hill, H., and Jurafsky, D. (2022). Computationally identifying funneling and focusing questions in classroom discourse. In Proceedings of the 17th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2022), pages 224–233. Association for Computational Linguistics (ACL).
Almubarak, A., Alhalabi, W., Albidewi, I., and Alharbi, E. (2024). An analytical approach for an ai-based teacher performance evaluation system in saudi arabia's schools. Discover Applied Sciences, 6(406). Published online: 29 July 2024.
Breiman, L., Friedman, J. H., Olshen, R. A., and Stone, C. J. (1984). Classification and Regression Trees. Wadsworth, Belmont, CA.
Cao, J., Suresh, A., Jacobs, J., Clevenger, C., Howard, A., Brown, C., Milne, B., Fischaber, T., Sumner, T., and Martin, J. H. (2025). Enhancing talk moves analysis in mathematics tutoring through classroom teaching discourse. In Proceedings of the 31st International Conference on Computational Linguistics (COLING 2025), pages 7710–7725, Abu Dhabi. Association for Computational Linguistics (ACL).
Chanchal, A. and Zualkernan, I. (2022). Exploring semi-supervised learning for audio-based automated classroom observations. In Proceedings of the 19th International Conference on Cognition and Exploratory Learning in the Digital Age, CELDA 2022, pages 241–250, Portugal. IADIS Press.
Cohen, D. K. (2011). Teaching and Its Predicaments. Harvard University Press, Cambridge, MA.
Cortes, C. and Vapnik, V. (1995). Support vector networks. Machine Learning, 20(3):273–297.
Cover, T. and Hart, P. (1967). Nearest neighbor pattern classification. IEEE Transactions on Information Theory, 13(1):21–27.
Danielson, C. (2007). The Framework for Teaching. ASCD.
Deerwester, S., Dumais, S. T., Furnas, G. W., Landauer, T. K., and Harshman, R. (1990). Indexing by latent semantic analysis. Journal of the American Society for Information Science, 41(6):391–407.
Demszky, D. and Hill, H. (2023). The NCTE transcripts: A dataset of elementary math classroom transcripts. In Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023), pages 528–538, Toronto, Canada. Association for Computational Linguistics (ACL).
Dietterich, T. G. (2000). Ensemble methods in machine learning. In International Workshop on Multiple Classifier Systems, pages 1–15.
Grossman, P., Compton, C., Igra, D., Ronfeldt, M., Shahan, E., and Williamson, P. W. (2009). Teaching practice: A cross-professional perspective. Teachers College Record, 111(9):2055–2100.
Gunasekara, S. and Saarela, M. (2025). Explainable ai in education: Techniques and qualitative assessment. Applied Sciences, 15(3):1239.
Halko, N., Martinsson, P.-G., and Tropp, J. A. (2011). Finding structure with randomness: Probabilistic algorithms for constructing approximate matrix decompositions. SIAM Review, 53(2):217–288.
Hattie, J. (2009). Visible learning: A synthesis of over 800 meta-analyses relating to achievement. Routledge.
Long, Y., Luo, H., and Zhang, Y. (2024). Evaluating large language models in analysing classroom dialogue. npj Science of Learning, 9(1):60.
Lundberg, S. M. and Lee, S.-I. (2017). A unified approach to interpreting model predictions. In Advances in Neural Information Processing Systems (NeurIPS), volume 30, pages 4765–4774.
MacQueen, J. (1967). Some methods for classification and analysis of multivariate observations. In Proceedings of the 5th Berkeley Symposium on Mathematical Statistics and Probability, volume 1, pages 281–297.
Manning, C. D., Raghavan, P., and Schütze, H. (2008). Introduction to Information Retrieval. Cambridge University Press.
Michaels, S., O'Connor, C., and Resnick, L. B. (2008). Deliberative discourse idealized and realized: Accountable talk in the classroom and in civic life. Studies in Philosophy and Education, 27(4):283–297.
Mitchell, T. M. (1997). Machine Learning. McGraw-Hill.
Ninin, M. O. G. a. (2009). A atividade de observação nas práticas de orientação a professores: uma perspectiva crítica. DELTA: Documentação de Estudos em Linguística Teórica e Aplicada, 25(2):253–282.
Oliveira, M., Cabral, L. d. S., and Mello, R. F. (2024). Análise de modelos de aprendizado de máquina para a predição do desempenho de alunos com enfoque na detecção de viés algorítmico. In Anais do XXXV Simpósio Brasileiro de Informática na Educação (SBIE 2024), Rio de Janeiro. Sociedade Brasileira de Computação (SBC).
Pianta, R. C., La Paro, K. M., and Hamre, B. K. (2008). Classroom Assessment Scoring System (CLASS). Paul H. Brookes Publishing Co.
Rumelhart, D. E., Hinton, G. E., and Williams, R. J. (1986). Learning representations by back-propagating errors. Nature, 323(6088):533–536.
Shulman, L. S. (1987). Knowledge and teaching: Foundations of the new reform. Harvard Educational Review, 57(1):1–22.
Sparck Jones, K. (1972). A statistical interpretation of term specificity and its application in retrieval. Journal of Documentation, 28(1):11–21.
Stallings, J. A. (1977). The Stallings Classroom Observation System. Stanford University Press.
Suresh, A., Jacobs, J., Harty, C., Perkoff, M., Martin, J. H., and Sumner, T. (2022). The talkmoves dataset: K–12 mathematics lesson transcripts annotated for teacher and student discursive moves. In Proceedings of the 13th Language Resources and Evaluation Conference (LREC), pages 4654–4662, Marseille. European Language Resources Association.
Suresh, A., Jacobs, J., Lai, V., Tan, C., Ward, W., Martin, J. H., and Sumner, T. (2021). Using transformers to provide teachers with personalized feedback on their classroom discourse: The talkmoves application. In Proceedings of the AAAI 2021 Spring Symposium on Artificial Intelligence for K-12 Education. arXiv:2105.07949.
Suresh, A., Sumner, T., Jacobs, J., Foland, B., and Ward, W. (2019). Automating analysis and feedback to improve mathematics teachers' classroom discourse. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, pages 9721–9728.
Tran, N., Pierce, B., Litman, D., Correnti, R., and Matsumura, L. C. (2024). Analyzing large language models for classroom discussion assessment. In Proceedings of the 17th International Conference on Educational Data Mining (EDM 2024), pages 500–508. International Educational Data Mining Society.
Türkmen, G. (2025). The review of studies on explainable artificial intelligence in educational research. Journal of Educational Computing Research.
Wolpert, D. H. (1992). Stacked generalization. Neural Networks, 5(2):241–259.
Almubarak, A., Alhalabi, W., Albidewi, I., and Alharbi, E. (2024). An analytical approach for an ai-based teacher performance evaluation system in saudi arabia's schools. Discover Applied Sciences, 6(406). Published online: 29 July 2024.
Breiman, L., Friedman, J. H., Olshen, R. A., and Stone, C. J. (1984). Classification and Regression Trees. Wadsworth, Belmont, CA.
Cao, J., Suresh, A., Jacobs, J., Clevenger, C., Howard, A., Brown, C., Milne, B., Fischaber, T., Sumner, T., and Martin, J. H. (2025). Enhancing talk moves analysis in mathematics tutoring through classroom teaching discourse. In Proceedings of the 31st International Conference on Computational Linguistics (COLING 2025), pages 7710–7725, Abu Dhabi. Association for Computational Linguistics (ACL).
Chanchal, A. and Zualkernan, I. (2022). Exploring semi-supervised learning for audio-based automated classroom observations. In Proceedings of the 19th International Conference on Cognition and Exploratory Learning in the Digital Age, CELDA 2022, pages 241–250, Portugal. IADIS Press.
Cohen, D. K. (2011). Teaching and Its Predicaments. Harvard University Press, Cambridge, MA.
Cortes, C. and Vapnik, V. (1995). Support vector networks. Machine Learning, 20(3):273–297.
Cover, T. and Hart, P. (1967). Nearest neighbor pattern classification. IEEE Transactions on Information Theory, 13(1):21–27.
Danielson, C. (2007). The Framework for Teaching. ASCD.
Deerwester, S., Dumais, S. T., Furnas, G. W., Landauer, T. K., and Harshman, R. (1990). Indexing by latent semantic analysis. Journal of the American Society for Information Science, 41(6):391–407.
Demszky, D. and Hill, H. (2023). The NCTE transcripts: A dataset of elementary math classroom transcripts. In Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023), pages 528–538, Toronto, Canada. Association for Computational Linguistics (ACL).
Dietterich, T. G. (2000). Ensemble methods in machine learning. In International Workshop on Multiple Classifier Systems, pages 1–15.
Grossman, P., Compton, C., Igra, D., Ronfeldt, M., Shahan, E., and Williamson, P. W. (2009). Teaching practice: A cross-professional perspective. Teachers College Record, 111(9):2055–2100.
Gunasekara, S. and Saarela, M. (2025). Explainable ai in education: Techniques and qualitative assessment. Applied Sciences, 15(3):1239.
Halko, N., Martinsson, P.-G., and Tropp, J. A. (2011). Finding structure with randomness: Probabilistic algorithms for constructing approximate matrix decompositions. SIAM Review, 53(2):217–288.
Hattie, J. (2009). Visible learning: A synthesis of over 800 meta-analyses relating to achievement. Routledge.
Long, Y., Luo, H., and Zhang, Y. (2024). Evaluating large language models in analysing classroom dialogue. npj Science of Learning, 9(1):60.
Lundberg, S. M. and Lee, S.-I. (2017). A unified approach to interpreting model predictions. In Advances in Neural Information Processing Systems (NeurIPS), volume 30, pages 4765–4774.
MacQueen, J. (1967). Some methods for classification and analysis of multivariate observations. In Proceedings of the 5th Berkeley Symposium on Mathematical Statistics and Probability, volume 1, pages 281–297.
Manning, C. D., Raghavan, P., and Schütze, H. (2008). Introduction to Information Retrieval. Cambridge University Press.
Michaels, S., O'Connor, C., and Resnick, L. B. (2008). Deliberative discourse idealized and realized: Accountable talk in the classroom and in civic life. Studies in Philosophy and Education, 27(4):283–297.
Mitchell, T. M. (1997). Machine Learning. McGraw-Hill.
Ninin, M. O. G. a. (2009). A atividade de observação nas práticas de orientação a professores: uma perspectiva crítica. DELTA: Documentação de Estudos em Linguística Teórica e Aplicada, 25(2):253–282.
Oliveira, M., Cabral, L. d. S., and Mello, R. F. (2024). Análise de modelos de aprendizado de máquina para a predição do desempenho de alunos com enfoque na detecção de viés algorítmico. In Anais do XXXV Simpósio Brasileiro de Informática na Educação (SBIE 2024), Rio de Janeiro. Sociedade Brasileira de Computação (SBC).
Pianta, R. C., La Paro, K. M., and Hamre, B. K. (2008). Classroom Assessment Scoring System (CLASS). Paul H. Brookes Publishing Co.
Rumelhart, D. E., Hinton, G. E., and Williams, R. J. (1986). Learning representations by back-propagating errors. Nature, 323(6088):533–536.
Shulman, L. S. (1987). Knowledge and teaching: Foundations of the new reform. Harvard Educational Review, 57(1):1–22.
Sparck Jones, K. (1972). A statistical interpretation of term specificity and its application in retrieval. Journal of Documentation, 28(1):11–21.
Stallings, J. A. (1977). The Stallings Classroom Observation System. Stanford University Press.
Suresh, A., Jacobs, J., Harty, C., Perkoff, M., Martin, J. H., and Sumner, T. (2022). The talkmoves dataset: K–12 mathematics lesson transcripts annotated for teacher and student discursive moves. In Proceedings of the 13th Language Resources and Evaluation Conference (LREC), pages 4654–4662, Marseille. European Language Resources Association.
Suresh, A., Jacobs, J., Lai, V., Tan, C., Ward, W., Martin, J. H., and Sumner, T. (2021). Using transformers to provide teachers with personalized feedback on their classroom discourse: The talkmoves application. In Proceedings of the AAAI 2021 Spring Symposium on Artificial Intelligence for K-12 Education. arXiv:2105.07949.
Suresh, A., Sumner, T., Jacobs, J., Foland, B., and Ward, W. (2019). Automating analysis and feedback to improve mathematics teachers' classroom discourse. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, pages 9721–9728.
Tran, N., Pierce, B., Litman, D., Correnti, R., and Matsumura, L. C. (2024). Analyzing large language models for classroom discussion assessment. In Proceedings of the 17th International Conference on Educational Data Mining (EDM 2024), pages 500–508. International Educational Data Mining Society.
Türkmen, G. (2025). The review of studies on explainable artificial intelligence in educational research. Journal of Educational Computing Research.
Wolpert, D. H. (1992). Stacked generalization. Neural Networks, 5(2):241–259.
Publicado
05/10/2026
Como Citar
DO AMARAL, Alex Almeida; DA SILVA, Huliane Medeiros; CHALLCO, Geiser Chalco.
Classificação Automática de Movimentos Pedagógicos como Apoio à Análise e à Avaliação da Prática Docente: Um Estudo com a Base TalkMoves. In: SIMPÓSIO BRASILEIRO DE INFORMÁTICA NA EDUCAÇÃO (SBIE), 37. , 2026, Goiânia/GO.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 730-744.
DOI: https://doi.org/10.5753/sbie.2026.27292.
