Use of Large Language Models in the Teaching of Computational Thinking: A Systematic Mapping Study
Resumo
This study presents the results of a systematic mapping of the use of Large Language Models (LLMs) in Computational Thinking (CT) education. The study was designed using the Goal–Question–Metric approach and well-known secondary study guidelines. A final set of 13 primary studies was selected from 10,022 records retrieved from Scopus, IEEE Xplore, and the ACM Digital Library. This study provides an overview of technological configurations, pedagogical practices, learning outcomes, evaluation strategies, and educational contexts in which LLMs have been used in CT education. Results show that LLMs are most commonly utilized as evaluators, feedback generators, and intelligent tutors, with emerging applications in pair programming and scaffolding. Pedagogical approaches favor structured support and projector design-based learning, with teachers acting primarily as facilitators and intervention designers and students as the main protagonists of their education. LLMs’ adoption is growing in higher education, while adoption at primary and secondary levels remains underexplored. Most interventions take place in synchronous, face-to-face formats and display substantial variation in evaluation rigor. Key gaps include limited use of validated knowledge assessment tools and insufficient attention to teacher preparation for hybrid human–AI instruction. These findings inform future research, design, and policy for AI-enhanced computing education.
Referências
Basili, V. R. and Weiss, D. M. (1984). A methodology for collecting valid software engineering data. IEEE Transactions on Software Engineering, SE-10(6):728–738.
Benavides-Varela, S., Callegher, C. Z., Fagiolini, B., Leo, I., Altoè, G., and Lucangeli, D. (2020). Effectiveness of digital-based interventions for children with mathematical learning difficulties: A meta-analysis. Computers & Education, 157:103953.
Brennan, K. and Resnick, M. (2012). New frameworks for studying and assessing the development of computational thinking. In Proceedings of the 2012 annual meeting of the American educational research association, Vancouver, Canada, volume 1, page 25.
Dawson, M. G., Deer, R., and Boguslawski, S. (2025). Cognitive dissonance in programming education: A qualitative exploration of the impact of generative ai on application-directed learning. Computers in Human Behavior Reports, page 100724.
Elnaffar, S., Rashidi, F., and Abualkishik, A. Z. (2025). Teaching with ai: A systematic review of chatbots, generative tools, and tutoring systems in programming education.
Felizardo, K. R., Nakagawa, E. Y., Scannavino, Fabbri, S. C. P. F., and Ferrari, F. C. (2017). Revisão Sistemática da Literatura em Engenharia de Software: Teoria e Prática. Elsevier Brasil, Rio de Janeiro, 1 edition.
Grover, S. and Pea, R. (2013). Computational thinking in k–12 a review of the state of the field. Educational Researcher, 42:38–43.
Heung, Y. M. E. and Chiu, T. K. (2025). How chatgpt impacts student engagement from a systematic review and meta-analysis study. Computers and Education: Artificial Intelligence, 8:100361.
Hong, S.-J., Lee, Y., and Kim, S.-W. (2024). Effect of artificial intelligence convergence education using chatgpt on computational thinking of high school students in korea. International Journal on Advanced Science, Engineering & Information Technology, 14(6).
Husaeni, A., Fitria, D., Abdullah, A. G., Septem Riza, L., Suherman, A., Husaeni, A., Novia, D., et al. (2025). Trends and impacts of artificial intelligence application in the development of computational thinking skills. Informatics in Education, 24(2):261–298.
Kitchenham, B. A., Budgen, D., and Brereton, P. (2015). Evidence-based software engineering and systematic reviews. CRC press.
Korkmaz, Ö., Çakir, R., and Özden, M. Y. (2017). A validity and reliability study of the computational thinking scales (cts). Computers in human behavior, 72:558–569.
Lei, Y., Liu, J., Fu, X., Zhao, J., and Yi, B. (2025). The effects of a generative ai-enabled cdio teaching model on undergraduates’ computational thinking and individual psychological constructs. Computer Applications in Engineering Education, 33(5):e70075.
Li, Y., Yang, R., Gui, S., Shi, P., Huang, X., Yang, D., Zhang, X., and Gai, Y. (2024). Visualizing program behavior: A study of enhanced program diagrams using llm. In 2024 IEEE Frontiers in Education Conference (FIE), pages 1–5. IEEE.
Li, Y., Zhou, X., and Chiu, T. K. (2025a). Systematics review on artificial intelligence chatbots and chatgpt for language learning and research from self-determination theory (sdt): what are the roles of teachers? Interactive Learning Environments, 33(3):1850–1864.
Li, Z., Zheng, X., and Fu, Q. (2025b). Exploring the computational thinking process of college students: Collaborative programming with llms. In 2025 7th International Conference on Computer Science and Technologies in Education (CSTE), pages 6–10. IEEE.
Liao, J., Zhong, L., Zhe, L., Xu, H., Liu, M., and Xie, T. (2024). Scaffolding computational thinking with chatgpt. IEEE Transactions on Learning Technologies, 17:1628–1642.
Miao, F. and Holmes, W. (2023). Guidance for generative ai in education and research. Technical report, UNESCO.
Nathaniel, J., Oyelere, S. S., Suhonen, J., and Tedre, M. (2025). Investigating the impact of generative ai integration on the sustenance of higher-order thinking skills and understanding of programming logic in programming education. Computers and Education: Artificial Intelligence, page 100460.
Ouaazki, A., Bergram, K., and Holzer, A. (2023). Leveraging chatgpt to enhance computational thinking learning experiences. In 2023 IEEE International Conference on Teaching, Assessment and Learning for Engineering (TALE), pages 1–7. IEEE.
Petersen, K., Feldt, R., Mujtaba, S., and Mattsson, M. (2008). Systematic mapping studies in software engineering. In 12th International Conference on Evaluation and Assessment in Software Engineering (EASE), pages 1–10. BCS, BCS Learning & Events Ltd.
Raihan, N., Siddiq, M. L., Santos, J. C. S., and Zampieri, M. (2024). Large language models in computer science education: A systematic literature review.
Sanchez, J. A., Flores-Eraña, G., Silva-Campos, J. M., Chavira-Quintero, R., and Olais-Govea, J. M. (2025). Generative ai as a cognitive mediator: A critical-constructivist inquiry into computational thinking in secondary education. In Frontiers in Education, volume 10, page 1597249. Frontiers.
Wing, J. M. (2006). Computational thinking. Communications of the ACM, 49(3):33–35.
Yan, Y.-M., Chen, C.-Q., Hu, Y.-B., and Ye, X.-D. (2025). Llm-based collaborative programming: impact on students’ computational thinking and self-efficacy. Humanities and Social Sciences Communications, 12(1):1–12.
Yunianto, W., Lavicza, Z., Kastner-Hauler, O., and Houghton, T. (2024). Investigating the use of chatgpt to solve a geogebra based mathematics+ computational thinking task in a geometry topic. Journal on Mathematics Education.
Zhan, Z., He, L., Tong, Y., Liang, X., Guo, S., and Lan, X. (2022). The effectiveness of gamification in programming education: Evidence from a meta-analysis. Computers and Education: Artificial Intelligence, 3:100096.
Zhang, X., Zhang, P., Shen, Y., Liu, M., Qiong, W., Gasevic, D., and Fan, Y. (2024). A systematic literature review of empirical research on applying generative artificial intelligence in education. Frontiers of Digital Education, 1:223–245.
Zhao, J.-H., Shangguan, S.-T., and Wang, Y. (2025). Exploring the effects of the cer model-based genai learning system to cultivate elementary school students’ computational thinking core skills in science courses. Journal of Computer Assisted Learning, 41(5):e70110.
Zönnchen, B., Hobelsberger, M., Socher, G., Thurner, V., and Ottinger, S. (2025). Exploring the role of large language models as artificial tutors. In 2025 IEEE Global Engineering Education Conference (EDUCON), pages 1–10. IEEE.
Benavides-Varela, S., Callegher, C. Z., Fagiolini, B., Leo, I., Altoè, G., and Lucangeli, D. (2020). Effectiveness of digital-based interventions for children with mathematical learning difficulties: A meta-analysis. Computers & Education, 157:103953.
Brennan, K. and Resnick, M. (2012). New frameworks for studying and assessing the development of computational thinking. In Proceedings of the 2012 annual meeting of the American educational research association, Vancouver, Canada, volume 1, page 25.
Dawson, M. G., Deer, R., and Boguslawski, S. (2025). Cognitive dissonance in programming education: A qualitative exploration of the impact of generative ai on application-directed learning. Computers in Human Behavior Reports, page 100724.
Elnaffar, S., Rashidi, F., and Abualkishik, A. Z. (2025). Teaching with ai: A systematic review of chatbots, generative tools, and tutoring systems in programming education.
Felizardo, K. R., Nakagawa, E. Y., Scannavino, Fabbri, S. C. P. F., and Ferrari, F. C. (2017). Revisão Sistemática da Literatura em Engenharia de Software: Teoria e Prática. Elsevier Brasil, Rio de Janeiro, 1 edition.
Grover, S. and Pea, R. (2013). Computational thinking in k–12 a review of the state of the field. Educational Researcher, 42:38–43.
Heung, Y. M. E. and Chiu, T. K. (2025). How chatgpt impacts student engagement from a systematic review and meta-analysis study. Computers and Education: Artificial Intelligence, 8:100361.
Hong, S.-J., Lee, Y., and Kim, S.-W. (2024). Effect of artificial intelligence convergence education using chatgpt on computational thinking of high school students in korea. International Journal on Advanced Science, Engineering & Information Technology, 14(6).
Husaeni, A., Fitria, D., Abdullah, A. G., Septem Riza, L., Suherman, A., Husaeni, A., Novia, D., et al. (2025). Trends and impacts of artificial intelligence application in the development of computational thinking skills. Informatics in Education, 24(2):261–298.
Kitchenham, B. A., Budgen, D., and Brereton, P. (2015). Evidence-based software engineering and systematic reviews. CRC press.
Korkmaz, Ö., Çakir, R., and Özden, M. Y. (2017). A validity and reliability study of the computational thinking scales (cts). Computers in human behavior, 72:558–569.
Lei, Y., Liu, J., Fu, X., Zhao, J., and Yi, B. (2025). The effects of a generative ai-enabled cdio teaching model on undergraduates’ computational thinking and individual psychological constructs. Computer Applications in Engineering Education, 33(5):e70075.
Li, Y., Yang, R., Gui, S., Shi, P., Huang, X., Yang, D., Zhang, X., and Gai, Y. (2024). Visualizing program behavior: A study of enhanced program diagrams using llm. In 2024 IEEE Frontiers in Education Conference (FIE), pages 1–5. IEEE.
Li, Y., Zhou, X., and Chiu, T. K. (2025a). Systematics review on artificial intelligence chatbots and chatgpt for language learning and research from self-determination theory (sdt): what are the roles of teachers? Interactive Learning Environments, 33(3):1850–1864.
Li, Z., Zheng, X., and Fu, Q. (2025b). Exploring the computational thinking process of college students: Collaborative programming with llms. In 2025 7th International Conference on Computer Science and Technologies in Education (CSTE), pages 6–10. IEEE.
Liao, J., Zhong, L., Zhe, L., Xu, H., Liu, M., and Xie, T. (2024). Scaffolding computational thinking with chatgpt. IEEE Transactions on Learning Technologies, 17:1628–1642.
Miao, F. and Holmes, W. (2023). Guidance for generative ai in education and research. Technical report, UNESCO.
Nathaniel, J., Oyelere, S. S., Suhonen, J., and Tedre, M. (2025). Investigating the impact of generative ai integration on the sustenance of higher-order thinking skills and understanding of programming logic in programming education. Computers and Education: Artificial Intelligence, page 100460.
Ouaazki, A., Bergram, K., and Holzer, A. (2023). Leveraging chatgpt to enhance computational thinking learning experiences. In 2023 IEEE International Conference on Teaching, Assessment and Learning for Engineering (TALE), pages 1–7. IEEE.
Petersen, K., Feldt, R., Mujtaba, S., and Mattsson, M. (2008). Systematic mapping studies in software engineering. In 12th International Conference on Evaluation and Assessment in Software Engineering (EASE), pages 1–10. BCS, BCS Learning & Events Ltd.
Raihan, N., Siddiq, M. L., Santos, J. C. S., and Zampieri, M. (2024). Large language models in computer science education: A systematic literature review.
Sanchez, J. A., Flores-Eraña, G., Silva-Campos, J. M., Chavira-Quintero, R., and Olais-Govea, J. M. (2025). Generative ai as a cognitive mediator: A critical-constructivist inquiry into computational thinking in secondary education. In Frontiers in Education, volume 10, page 1597249. Frontiers.
Wing, J. M. (2006). Computational thinking. Communications of the ACM, 49(3):33–35.
Yan, Y.-M., Chen, C.-Q., Hu, Y.-B., and Ye, X.-D. (2025). Llm-based collaborative programming: impact on students’ computational thinking and self-efficacy. Humanities and Social Sciences Communications, 12(1):1–12.
Yunianto, W., Lavicza, Z., Kastner-Hauler, O., and Houghton, T. (2024). Investigating the use of chatgpt to solve a geogebra based mathematics+ computational thinking task in a geometry topic. Journal on Mathematics Education.
Zhan, Z., He, L., Tong, Y., Liang, X., Guo, S., and Lan, X. (2022). The effectiveness of gamification in programming education: Evidence from a meta-analysis. Computers and Education: Artificial Intelligence, 3:100096.
Zhang, X., Zhang, P., Shen, Y., Liu, M., Qiong, W., Gasevic, D., and Fan, Y. (2024). A systematic literature review of empirical research on applying generative artificial intelligence in education. Frontiers of Digital Education, 1:223–245.
Zhao, J.-H., Shangguan, S.-T., and Wang, Y. (2025). Exploring the effects of the cer model-based genai learning system to cultivate elementary school students’ computational thinking core skills in science courses. Journal of Computer Assisted Learning, 41(5):e70110.
Zönnchen, B., Hobelsberger, M., Socher, G., Thurner, V., and Ottinger, S. (2025). Exploring the role of large language models as artificial tutors. In 2025 IEEE Global Engineering Education Conference (EDUCON), pages 1–10. IEEE.
Publicado
04/05/2026
Como Citar
MILHORIM, João Antônio Misson; SANTANA, Diego Gomes de; LEMOS, Diego Fernandes; GARCÉS, Lina.
Use of Large Language Models in the Teaching of Computational Thinking: A Systematic Mapping Study. In: SIMPÓSIO BRASILEIRO DE EDUCAÇÃO EM COMPUTAÇÃO (EDUCOMP), 6. , 2026, Campo Grande/MS.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 257-271.
ISSN 3086-0733.
DOI: https://doi.org/10.5753/educomp.2026.18797.
