Padrões de Interação em Tutoria por IA: Perfis Conversacionais Compatíveis com Aprendizagem Autorregulada
Resumo
Este artigo investiga se rastros interacionais de diálogos com tutores baseados em Inteligência Artificial podem revelar perfis comportamentais interpretáveis compatíveis com processos de aprendizagem autorregulada. Analisamos o conjunto de dados público StudyChat, composto por 2.214 conversas de 203 estudantes distribuídas em sete atividades de programação de uma disciplina universitária de Inteligência Artificial. As mensagens dos estudantes foram mapeadas em atos de fala e modeladas como matrizes de transição de cadeias de Markov de primeira e segunda ordem no nível estudante-atividade. Após vetorização, padronização, redução de dimensionalidade com UMAP e clusterização com K-means, os grupos resultantes foram interpretados com apoio de métricas estruturais e modelos de processo extraídos com Heuristic Miner. A representação de segunda ordem produziu a solução mais coerente, com seis perfis de interação que variam de comportamentos rígidos e diretivos a padrões densamente exploratórios. Uma análise longitudinal baseada em distância de Hamming mascarada mostrou que muitos estudantes transitam entre perfis ao longo das atividades, em vez de permanecerem em um modo único e estável. Como principal contribuição, o estudo apresenta um pipeline explicável de learning analytics para dados conversacionais educacionais e mostra como esses rastros podem sustentar interpretações cautelosas, teoricamente informadas e relevantes para tutores por IA adaptativos.
Palavras-chave:
Learning analytics, aprendizagem autorregulada, tutoria por IA, atos de fala, mineração de processos
Referências
Allaoui, M., Kherfi, M. L., and Cheriet, A. (2020). Considerably improving clustering algorithms using UMAP dimensionality reduction technique: A comparative study. In El Moataz, A., Mammass, D., Mansouri, A., and Nouboud, F., editors, Image and Signal Processing: 9th International Conference, ICISP 2020, Marrakesh, Morocco, June 4–6, 2020, Proceedings, volume 12119 of Lecture Notes in Computer Science, pages 317–325, Cham. Springer International Publishing.
Azevedo, R., Bouchet, F., Duffy, M., Harley, J., Taub, M., Trevors, G., Cloude, E., Dever, D., Wiedbusch, M., Wortha, F., and Cerezo, R. (2022). Lessons learned and future directions of metatutor: Leveraging multichannel data to scaffold self-regulated learning with an intelligent tutoring system. Frontiers in Psychology, Volume 13 - 2022.
Devlin, J., Chang, M.-W., Lee, K., and Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. In Burstein, J., Doran, C., and Solorio, T., editors, Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 4171–4186, Minneapolis, Minnesota. Association for Computational Linguistics.
Duran, N., Battle, S., and Smith, J. (2023). Sentence encoding for dialogue act classification. Natural Language Engineering, 29(3):794–823.
Gao, J., Li, S., Zhang, J., Li, S., and Wang, T. (2026). Investigating self-regulated learning sequences within a generative ai-based intelligent tutoring system. In Proceedings of the LAK26: 16th International Learning Analytics and Knowledge Conference, LAK '26, pages 905–911, New York, NY, USA. Association for Computing Machinery.
Keuning, H., Jeuring, J., and Heeren, B. (2018). A systematic literature review of automated feedback generation for programming exercises. ACM Trans. Comput. Educ., 19(1).
Kinnebrew, J. S., Loretz, K. M., and Biswas, G. (2013). A contextualized, differential sequence mining method to derive students' learning behavior patterns. Journal of Educational Data Mining, 5(1).
Labadze, L., Grigolia, M., and Machaidze, L. (2023). Role of AI chatbots in education: Systematic literature review. International Journal of Educational Technology in Higher Education, 20(1):56.
Maldonado-Mahauad, J., Pérez-Sanagustín, M., Kizilcec, R. F., Morales, N., and Muñoz-Gama, J. (2018). Mining theory-based patterns from big data: Identifying self-regulated learning strategies in massive open online courses. Computers in Human Behavior, 80:179–196.
McNichols, H., Ikram, F., and Lan, A. (2026). The studychat dataset: Analyzing student dialogues with chatgpt in an artificial intelligence course. In Proceedings of the LAK26: 16th International Learning Analytics and Knowledge Conference, LAK '26, page 53–63, New York, NY, USA. Association for Computing Machinery.
Poitras, E. G., Doleck, T., Huang, L., Dias, L., and Lajoie, S. P. (2023). Time-driven modeling of student self-regulated learning in network-based tutors. Interactive Learning Environments, 31(4):2490–2511.
Procter, M., Lin, F., and Heller, B. (2018). Intelligent intervention by conversational agent through chatlog analysis. Smart Learning Environments, 5(1):30.
Roll, I., Aleven, V., McLaren, B. M., and Koedinger, K. R. (2011). Improving students' help-seeking skills using metacognitive feedback in an intelligent tutoring system. Learning and Instruction, 21(2):267–280.
Tang, Y., Li, Z., Wang, G., and Hu, X. (2023). Modeling learning behaviors and predicting performance in an intelligent tutoring system: a two-layer hidden markov modeling approach. Interactive Learning Environments, 31(9):5495–5507.
Villalobos, E., Pérez-Sanagustín, M., Azevedo, R., Sanza, C., and Broisin, J. (2024). Exploring manifestations of learners' self-regulated tactics and strategies across blended learning courses. IEEE Transactions on Learning Technologies, 17:1544–1557.
Wei, J., Dang, D. K., Yang, K., Stokes, E., Mazeh, A., Lim, A., Dai, D. W., Moore, J., Fan, Y., Gasevic, D., Gasevic, D., and Chen, G. (2026). Uncovering students' inquiry patterns in genai-supported clinical practice: An integration of epistemic network analysis and sequential pattern mining. In Proceedings of the LAK26: 16th International Learning Analytics and Knowledge Conference, LAK '26, pages 261–271, New York, NY, USA. Association for Computing Machinery.
Winne, P. H. (2017). Learning analytics for self-regulated learning. In Lang, C., Siemens, G., Wise, A., and Gašević, D., editors, Handbook of Learning Analytics, pages 241–249. Society for Learning Analytics Research.
Wood, A., Rodeghero, P., Armaly, A., and McMillan, C. (2018). Detecting speech act types in developer question/answer conversations during bug repair. In Proceedings of the 2018 26th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, ESEC/FSE 2018, page 491–502, New York, NY, USA. Association for Computing Machinery.
Zimmerman, B. J. and Schunk, D. H. (2011). Self-regulated learning and performance: An introduction and an overview. In Handbook of Self-Regulation of Learning and Performance, pages 1–12. Routledge, New York, NY.
Azevedo, R., Bouchet, F., Duffy, M., Harley, J., Taub, M., Trevors, G., Cloude, E., Dever, D., Wiedbusch, M., Wortha, F., and Cerezo, R. (2022). Lessons learned and future directions of metatutor: Leveraging multichannel data to scaffold self-regulated learning with an intelligent tutoring system. Frontiers in Psychology, Volume 13 - 2022.
Devlin, J., Chang, M.-W., Lee, K., and Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. In Burstein, J., Doran, C., and Solorio, T., editors, Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 4171–4186, Minneapolis, Minnesota. Association for Computational Linguistics.
Duran, N., Battle, S., and Smith, J. (2023). Sentence encoding for dialogue act classification. Natural Language Engineering, 29(3):794–823.
Gao, J., Li, S., Zhang, J., Li, S., and Wang, T. (2026). Investigating self-regulated learning sequences within a generative ai-based intelligent tutoring system. In Proceedings of the LAK26: 16th International Learning Analytics and Knowledge Conference, LAK '26, pages 905–911, New York, NY, USA. Association for Computing Machinery.
Keuning, H., Jeuring, J., and Heeren, B. (2018). A systematic literature review of automated feedback generation for programming exercises. ACM Trans. Comput. Educ., 19(1).
Kinnebrew, J. S., Loretz, K. M., and Biswas, G. (2013). A contextualized, differential sequence mining method to derive students' learning behavior patterns. Journal of Educational Data Mining, 5(1).
Labadze, L., Grigolia, M., and Machaidze, L. (2023). Role of AI chatbots in education: Systematic literature review. International Journal of Educational Technology in Higher Education, 20(1):56.
Maldonado-Mahauad, J., Pérez-Sanagustín, M., Kizilcec, R. F., Morales, N., and Muñoz-Gama, J. (2018). Mining theory-based patterns from big data: Identifying self-regulated learning strategies in massive open online courses. Computers in Human Behavior, 80:179–196.
McNichols, H., Ikram, F., and Lan, A. (2026). The studychat dataset: Analyzing student dialogues with chatgpt in an artificial intelligence course. In Proceedings of the LAK26: 16th International Learning Analytics and Knowledge Conference, LAK '26, page 53–63, New York, NY, USA. Association for Computing Machinery.
Poitras, E. G., Doleck, T., Huang, L., Dias, L., and Lajoie, S. P. (2023). Time-driven modeling of student self-regulated learning in network-based tutors. Interactive Learning Environments, 31(4):2490–2511.
Procter, M., Lin, F., and Heller, B. (2018). Intelligent intervention by conversational agent through chatlog analysis. Smart Learning Environments, 5(1):30.
Roll, I., Aleven, V., McLaren, B. M., and Koedinger, K. R. (2011). Improving students' help-seeking skills using metacognitive feedback in an intelligent tutoring system. Learning and Instruction, 21(2):267–280.
Tang, Y., Li, Z., Wang, G., and Hu, X. (2023). Modeling learning behaviors and predicting performance in an intelligent tutoring system: a two-layer hidden markov modeling approach. Interactive Learning Environments, 31(9):5495–5507.
Villalobos, E., Pérez-Sanagustín, M., Azevedo, R., Sanza, C., and Broisin, J. (2024). Exploring manifestations of learners' self-regulated tactics and strategies across blended learning courses. IEEE Transactions on Learning Technologies, 17:1544–1557.
Wei, J., Dang, D. K., Yang, K., Stokes, E., Mazeh, A., Lim, A., Dai, D. W., Moore, J., Fan, Y., Gasevic, D., Gasevic, D., and Chen, G. (2026). Uncovering students' inquiry patterns in genai-supported clinical practice: An integration of epistemic network analysis and sequential pattern mining. In Proceedings of the LAK26: 16th International Learning Analytics and Knowledge Conference, LAK '26, pages 261–271, New York, NY, USA. Association for Computing Machinery.
Winne, P. H. (2017). Learning analytics for self-regulated learning. In Lang, C., Siemens, G., Wise, A., and Gašević, D., editors, Handbook of Learning Analytics, pages 241–249. Society for Learning Analytics Research.
Wood, A., Rodeghero, P., Armaly, A., and McMillan, C. (2018). Detecting speech act types in developer question/answer conversations during bug repair. In Proceedings of the 2018 26th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, ESEC/FSE 2018, page 491–502, New York, NY, USA. Association for Computing Machinery.
Zimmerman, B. J. and Schunk, D. H. (2011). Self-regulated learning and performance: An introduction and an overview. In Handbook of Self-Regulation of Learning and Performance, pages 1–12. Routledge, New York, NY.
Publicado
05/10/2026
Como Citar
MAIA NETO, Otacilio Saraiva; DE MELLO, Rafael Ferreira Leite; PONTUAL FALCÃO, Taciana; DO NASCIMENTO, André Câmara Alves.
Padrões de Interação em Tutoria por IA: Perfis Conversacionais Compatíveis com Aprendizagem Autorregulada. In: SIMPÓSIO BRASILEIRO DE INFORMÁTICA NA EDUCAÇÃO (SBIE), 37. , 2026, Goiânia/GO.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 219-232.
DOI: https://doi.org/10.5753/sbie.2026.26938.
