Aplicações de LLMs no ensino de Programação Orientada a Objetos: Um Mapeamento Sistemático da Literatura
Resumo
O uso de Grandes Modelos de Linguagem (LLMs) no ensino de programação têm crescido rapidamente, mas ainda são raros estudos secundários que contemplem a Programação Orientada a Objetos (POO). Este trabalho apresenta um Mapeamento Sistemático da Literatura para analisar como LLMs têm sido empregados no ensino de POO, quais modelos são utilizados e como suas aplicações são avaliadas. A partir de 18 estudos primários, observa-se predominância do uso de LLMs como ferramenta de apoio à resolução de exercícios, com destaque para o ChatGPT e integração a ambientes de desenvolvimento. As avaliações concentram-se em métricas de código e estudos de caso, com baixa incidência de experimentos controlados. Os achados indicam que o campo ainda se encontra em consolidação metodológica e demanda investigações que articulem desempenho técnico, aprendizagem conceitual e design instrucional.Referências
Alexandron, G., Armoni, M., Gordon, M., and Harel, D. (2014). Scenario-based programming: reducing the cognitive load, fostering abstract thinking. In Companion Proceedings of the 36th International Conference on Software Engineering, ICSE Companion 2014, page 311–320, New York, NY, USA. Association for Computing Machinery.
Alturki, R., Santos, J., Alliyu, U., Gan, J., and Guo, Z. A. (2025). Evaluating chatgpt to answer multi-modal exercises in computer science education. In Proceedings of the 2025 ACM Conference on Innovation and Technology in Computer Science Education (ITiCSE), pages 58–64. ACM.
Alves, J. V. B., Gonçalves, Y. T., and Silva, H. B. (2024). Use of chatbots in programming education: A scoping review. In Anais do XXXV Simpósio Brasileiro de Informática na Educação (SBIE 2024), Fortaleza, CE, Brasil. SBC.
Andersen-Kiel, N. and Linos, P. (2024). Using chatgpt in undergraduate computer science and software engineering courses: A students’ perspective. In IEEE Frontiers in Education Conference (FIE), San Francisco, USA. IEEE.
Batiha, Q., Majid, N. A. A., Sahari, N., and Ali, N. M. (2023). Analysis of the learning object-oriented programming factors. International Journal of Electrical and Computer Engineering (IJECE).
Berssanette, J. H. and de Francisco, A. C. (2022). Cognitive load theory in the context of teaching and learning computer programming: A systematic literature review. IEEE Transactions on Education, 65(3):440–449.
Biolchini, J., Mian, P. G., Natali, A. C. C., and Travassos, G. H. (2005). Systematic review in software engineering. Technical report, Technical Report, PESC/COPPE Universidade Federal do Rio de Janeiro. Acesso em: 13 maio 2025.
Boudjehem, R., Benyounes, A., and Lafifi, Y. (2023). Liss’nap: A peer-advising collaborative learning approach for object-oriented programming learning. Acta Infologica.
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., Agarwal, S., Herbert-Voss, A., Krueger, G., Henighan, T., Child, R., Ramesh, A., Ziegler, D., Wu, J., Winter, C., Hesse, C., Chen, M., Sigler, E., Litwin, M., Gray, S., Chess, B., Clark, J., Berner, C., McCandlish, S., Radford, A., Sutskever, I., and Amodei, D. (2020). Language models are few-shot learners. In Advances in Neural Information Processing Systems, volume 33.
Cambaz, D. and Zhang, X. (2024). Use of ai-driven code generation models in teaching and learning programming: a systematic literature review. In Proceedings of the 55th ACM Technical Symposium on Computer Science Education (SIGCSE ’24), SIGCSE 2024, pages 172–178, New York, NY, USA. Association for Computing Machinery.
Cipriano, B. P. (2024). Towards the integration of large language models in an objectoriented programming course. In Proceedings of the 2024 International Symposium on Computers in Education (SIIE), Lisbon, Portugal. IEEE.
Cipriano, B. P. and Alves, P. (2023). Gpt-3 vs object oriented programming assignments: An experience report. In Proceedings of the 2023 International Symposium on Computers in Education (SIIE), Lisbon, Portugal. IEEE.
Cipriano, B. P., Alves, P., and Denny, P. (2024). A picture is worth a thousand words: Exploring diagram and video-based oop exercises to counter llm over-reliance. In Proceedings of the 2024 Innovation and Technology in Computer Science Education V. 2 (ITiCSE), pages 1–2, Milan, Italy. ACM.
Cruzes, D. S. and Dyba, T. (2011). Recommended steps for thematic synthesis in software engineering. In 2011 international symposium on empirical software engineering and measurement, pages 275–284. IEEE.
Dosaru, D.-F., Simion, D.-M., Ignat, A.-H., Negreanu, L.-C., and Olteanu, A.-C. (2025). Using genai to assess design patterns in student-written code. IEEE Transactions on Learning Technologies.
Gehanno, J.-F., Rollin, L., and Darmoni, S. (2013). Is the coverage of google scholar enough to be used alone for systematic reviews. BMC medical informatics and decision making, 13(1):7.
Grévisse, C. (2024). Comparative quality analysis of gpt-based multiple choice question generation. In Florez, H. and Leon, M., editors, Applied Informatics. ICAI 2023, volume 1874 of Communications in Computer and Information Science, pages 435–447. Springer, Cham.
Guest, O., Suarez, M., Müller, B., van Meerkerk, E., Beverborg, A. O. G., de Haan, R., Elizondo, A. R., Blokpoel, M., Scharfenberg, N., Kleinherenbrink, A., et al. (2025). Against the uncritical adoption of’ai’technologies in academia. Digital Culture Education, 16(2).
Gumonan, K. M. V. C., Bernus, J. U., Godinez, V. A. L., and Sayson, J. J. Z. (2025). Chatgpt perception and usage in object-oriented programming of students from a philippine private university. In 2025 11th International Conference on Education and Training Technologies (ICETT), pages 50–56. IEEE.
Haindl, P. and Weinberger, G. (2024). Does chatgpt help novice programmers write better code? results from static code analysis. Journal of Software Engineering and Applications, 17(2):57–73.
Jain, S., Kapoor, V., and Mukherjee, S. (2024). Student-perceived cognitive load of llm-generated programming exercises. IEEE Transactions on Learning Technologies.
Kaleem, M., Hassan, M. A., and Khurshid, S. K. (2024). A machine learning-based adaptive feedback system to enhance programming skill using computational thinking. IEEE Access, 12:59431–59440.
Kitchenham, B. and Charters, S. (2007). Guidelines for performing systematic literature reviews in software engineering. Technical report, Keele University and Durham University Joint Report. Acesso em: 13 maio 2025.
Kosar, T., Ostojić, D., Liu, Y. D., and Mernik, M. (2023). Computer science education in chatgpt era: Experiences from an experiment in a programming course for novice programmers. Mathematics, 11(13).
Kumar, Y., Manikandan, A., Li, J., and Morreale, P. (2024). Optimizing large language models for auto-generation of programming quizzes. In 2024 17th International Conference on Software Engineering and Consortium (ISEC), pages 1–8. IEEE.
Lian, V., Varoy, E., and Giacaman, N. (2022). Learning object-oriented programming concepts through visual analogies. IEEE Transactions on Learning Technologies, 15:78–92.
Mailach, A., Gorgosch, D., Siegmund, N., et al. (2025). ”ok pal, we have to code that now”: Interaction patterns of programming beginners with a conversational chatbot. Empirical Software Engineering, 30(34).
Marques, D. and Morandini, M. (2024). Uso do chatgpt no contexto educacional: Uma revisão sistemática da literatura. In Anais do XXXV Simpósio Brasileiro de Informática na Educação (SBIE 2024), Brasília, Brasil. SBC.
Menolli, A. and Strik, B. (2025). Educational insights from code: Mapping learning challenges in object-oriented programming through code-based evidence.
Menolli, A., Strik, B., and Rodrigues, L. (2024). Teaching refactoring to improve code quality with chatgpt: An experience report in undergraduate lessons. In Anais do XXXVI Simpósio Brasileiro de Informática na Educação (SBIE 2024), Brasil. SBC.
P, M. M., Jain, V., Khandelwal, P., Kataruka, K., and Shah, Y. (2024). Intelligent learning analytics through e-learning. In Proceedings of the International Conference on Emerging Technologies in Computer Science for Interdisciplinary Applications (ICETCS), Bangalore, India. IEEE.
Petersen, K., Vakkalanka, S., and Kuzniarz, L. (2015). Guidelines for conducting systematic mapping studies in software engineering: An update. Information and Software Technology, 64:1–18.
Phung, T., Pădurean, V.-A., Cambronero, J., Gulwani, S., Kohn, T., Majumdar, R., Singla, A., and Soares, G. (2024). Rubric is all you need: Improving llm-based code evaluation with question-specific rubrics. In Proceedings of the XXIII Brazilian Symposium on Software Quality (SBQS 2024), pages 1–12. ACM.
Puigcercos i Vilar, G., Rashid, P., and Tonekaboni, N. H. (2025). Accessible and reliable ai coding tutors: Augmenting large language models with retrieval-augmented generation for java programming. In 2025 IEEE Global Engineering Education Conference (EDUCON), pages 1–8. IEEE.
Raihan, N., Siddiq, M. L., Santos, J. C., and Zampieri, M. (2025). Large language models in computer science education: A systematic literature review. In Proceedings of the 1st ACM Conference on Computing in Computer Science Education (SIGCSETS ’25), SIGCSETS 2025, pages 938–944, New York, NY, USA. Association for Computing Machinery.
Sim, T. Y. and Lau, S. L. (2022). Review on challenges and solutions in novice programming education. In 2022 IEEE International Conference on Computing (ICOCO), pages 55–61.
Speth, S., Meißner, N., and Becker, S. (2023). Investigating the use of ai-generated exercises for beginner and intermediate programming courses: A chatgpt case study. In Proceedings of the 2023 IEEE Global Engineering Education Conference (EDUCON), Vienna, Austria. IEEE.
Sweller, J. (1988). Cognitive load during problem solving: Effects on learning. Cognitive Science, 12(2):257–285.
Sweller, J., Ayres, P., and Kalyuga, S. (2011). Cognitive Load Theory. Springer, New York.
Torek, A., Sorensen, E., Hahle, N., and Kennington, C. (2024). A systematic evaluation of code-generating chatbots for use in undergraduate computer science education. In Proceedings of the 55th ACM Technical Symposium on Computer Science Education (SIGCSE), Portland, OR, USA. ACM.
Uysal, M. P. (2016). Evaluation of learning environments for object-oriented programming: measuring cognitive load with a novel measurement technique. Interactive Learning Environments, 24(7):1590–1609.
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., and Polosukhin, I. (2017). Attention is all you need. In Advances in Neural Information Processing Systems, volume 30.
Wohlin, C. (2014). Guidelines for snowballing in systematic literature studies and a replication in software engineering. In Proceedings of the 18th international conference on evaluation and assessment in software engineering, pages 1–10.
Xinogalos, S. (2015). Object-oriented design and programming: An investigation of novices’ conceptions on objects and classes. ACM Trans. Comput. Educ., 15(3).
y Fernandez, C. A. F., Sánchez-Soto, E., Cisnero, J. R. A., and Juárez-Ramírez, R. (2024). Exploring the frontier of software engineering education with chatbots. Programming and Computer Software, 50(8):796–815.
Yilmaz, R. and Yilmaz, F. G. K. (2023). Augmented intelligence in programming learning: Examining student views on the use of chatgpt for programming learning. Education and Information Technologies.
Alturki, R., Santos, J., Alliyu, U., Gan, J., and Guo, Z. A. (2025). Evaluating chatgpt to answer multi-modal exercises in computer science education. In Proceedings of the 2025 ACM Conference on Innovation and Technology in Computer Science Education (ITiCSE), pages 58–64. ACM.
Alves, J. V. B., Gonçalves, Y. T., and Silva, H. B. (2024). Use of chatbots in programming education: A scoping review. In Anais do XXXV Simpósio Brasileiro de Informática na Educação (SBIE 2024), Fortaleza, CE, Brasil. SBC.
Andersen-Kiel, N. and Linos, P. (2024). Using chatgpt in undergraduate computer science and software engineering courses: A students’ perspective. In IEEE Frontiers in Education Conference (FIE), San Francisco, USA. IEEE.
Batiha, Q., Majid, N. A. A., Sahari, N., and Ali, N. M. (2023). Analysis of the learning object-oriented programming factors. International Journal of Electrical and Computer Engineering (IJECE).
Berssanette, J. H. and de Francisco, A. C. (2022). Cognitive load theory in the context of teaching and learning computer programming: A systematic literature review. IEEE Transactions on Education, 65(3):440–449.
Biolchini, J., Mian, P. G., Natali, A. C. C., and Travassos, G. H. (2005). Systematic review in software engineering. Technical report, Technical Report, PESC/COPPE Universidade Federal do Rio de Janeiro. Acesso em: 13 maio 2025.
Boudjehem, R., Benyounes, A., and Lafifi, Y. (2023). Liss’nap: A peer-advising collaborative learning approach for object-oriented programming learning. Acta Infologica.
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., Agarwal, S., Herbert-Voss, A., Krueger, G., Henighan, T., Child, R., Ramesh, A., Ziegler, D., Wu, J., Winter, C., Hesse, C., Chen, M., Sigler, E., Litwin, M., Gray, S., Chess, B., Clark, J., Berner, C., McCandlish, S., Radford, A., Sutskever, I., and Amodei, D. (2020). Language models are few-shot learners. In Advances in Neural Information Processing Systems, volume 33.
Cambaz, D. and Zhang, X. (2024). Use of ai-driven code generation models in teaching and learning programming: a systematic literature review. In Proceedings of the 55th ACM Technical Symposium on Computer Science Education (SIGCSE ’24), SIGCSE 2024, pages 172–178, New York, NY, USA. Association for Computing Machinery.
Cipriano, B. P. (2024). Towards the integration of large language models in an objectoriented programming course. In Proceedings of the 2024 International Symposium on Computers in Education (SIIE), Lisbon, Portugal. IEEE.
Cipriano, B. P. and Alves, P. (2023). Gpt-3 vs object oriented programming assignments: An experience report. In Proceedings of the 2023 International Symposium on Computers in Education (SIIE), Lisbon, Portugal. IEEE.
Cipriano, B. P., Alves, P., and Denny, P. (2024). A picture is worth a thousand words: Exploring diagram and video-based oop exercises to counter llm over-reliance. In Proceedings of the 2024 Innovation and Technology in Computer Science Education V. 2 (ITiCSE), pages 1–2, Milan, Italy. ACM.
Cruzes, D. S. and Dyba, T. (2011). Recommended steps for thematic synthesis in software engineering. In 2011 international symposium on empirical software engineering and measurement, pages 275–284. IEEE.
Dosaru, D.-F., Simion, D.-M., Ignat, A.-H., Negreanu, L.-C., and Olteanu, A.-C. (2025). Using genai to assess design patterns in student-written code. IEEE Transactions on Learning Technologies.
Gehanno, J.-F., Rollin, L., and Darmoni, S. (2013). Is the coverage of google scholar enough to be used alone for systematic reviews. BMC medical informatics and decision making, 13(1):7.
Grévisse, C. (2024). Comparative quality analysis of gpt-based multiple choice question generation. In Florez, H. and Leon, M., editors, Applied Informatics. ICAI 2023, volume 1874 of Communications in Computer and Information Science, pages 435–447. Springer, Cham.
Guest, O., Suarez, M., Müller, B., van Meerkerk, E., Beverborg, A. O. G., de Haan, R., Elizondo, A. R., Blokpoel, M., Scharfenberg, N., Kleinherenbrink, A., et al. (2025). Against the uncritical adoption of’ai’technologies in academia. Digital Culture Education, 16(2).
Gumonan, K. M. V. C., Bernus, J. U., Godinez, V. A. L., and Sayson, J. J. Z. (2025). Chatgpt perception and usage in object-oriented programming of students from a philippine private university. In 2025 11th International Conference on Education and Training Technologies (ICETT), pages 50–56. IEEE.
Haindl, P. and Weinberger, G. (2024). Does chatgpt help novice programmers write better code? results from static code analysis. Journal of Software Engineering and Applications, 17(2):57–73.
Jain, S., Kapoor, V., and Mukherjee, S. (2024). Student-perceived cognitive load of llm-generated programming exercises. IEEE Transactions on Learning Technologies.
Kaleem, M., Hassan, M. A., and Khurshid, S. K. (2024). A machine learning-based adaptive feedback system to enhance programming skill using computational thinking. IEEE Access, 12:59431–59440.
Kitchenham, B. and Charters, S. (2007). Guidelines for performing systematic literature reviews in software engineering. Technical report, Keele University and Durham University Joint Report. Acesso em: 13 maio 2025.
Kosar, T., Ostojić, D., Liu, Y. D., and Mernik, M. (2023). Computer science education in chatgpt era: Experiences from an experiment in a programming course for novice programmers. Mathematics, 11(13).
Kumar, Y., Manikandan, A., Li, J., and Morreale, P. (2024). Optimizing large language models for auto-generation of programming quizzes. In 2024 17th International Conference on Software Engineering and Consortium (ISEC), pages 1–8. IEEE.
Lian, V., Varoy, E., and Giacaman, N. (2022). Learning object-oriented programming concepts through visual analogies. IEEE Transactions on Learning Technologies, 15:78–92.
Mailach, A., Gorgosch, D., Siegmund, N., et al. (2025). ”ok pal, we have to code that now”: Interaction patterns of programming beginners with a conversational chatbot. Empirical Software Engineering, 30(34).
Marques, D. and Morandini, M. (2024). Uso do chatgpt no contexto educacional: Uma revisão sistemática da literatura. In Anais do XXXV Simpósio Brasileiro de Informática na Educação (SBIE 2024), Brasília, Brasil. SBC.
Menolli, A. and Strik, B. (2025). Educational insights from code: Mapping learning challenges in object-oriented programming through code-based evidence.
Menolli, A., Strik, B., and Rodrigues, L. (2024). Teaching refactoring to improve code quality with chatgpt: An experience report in undergraduate lessons. In Anais do XXXVI Simpósio Brasileiro de Informática na Educação (SBIE 2024), Brasil. SBC.
P, M. M., Jain, V., Khandelwal, P., Kataruka, K., and Shah, Y. (2024). Intelligent learning analytics through e-learning. In Proceedings of the International Conference on Emerging Technologies in Computer Science for Interdisciplinary Applications (ICETCS), Bangalore, India. IEEE.
Petersen, K., Vakkalanka, S., and Kuzniarz, L. (2015). Guidelines for conducting systematic mapping studies in software engineering: An update. Information and Software Technology, 64:1–18.
Phung, T., Pădurean, V.-A., Cambronero, J., Gulwani, S., Kohn, T., Majumdar, R., Singla, A., and Soares, G. (2024). Rubric is all you need: Improving llm-based code evaluation with question-specific rubrics. In Proceedings of the XXIII Brazilian Symposium on Software Quality (SBQS 2024), pages 1–12. ACM.
Puigcercos i Vilar, G., Rashid, P., and Tonekaboni, N. H. (2025). Accessible and reliable ai coding tutors: Augmenting large language models with retrieval-augmented generation for java programming. In 2025 IEEE Global Engineering Education Conference (EDUCON), pages 1–8. IEEE.
Raihan, N., Siddiq, M. L., Santos, J. C., and Zampieri, M. (2025). Large language models in computer science education: A systematic literature review. In Proceedings of the 1st ACM Conference on Computing in Computer Science Education (SIGCSETS ’25), SIGCSETS 2025, pages 938–944, New York, NY, USA. Association for Computing Machinery.
Sim, T. Y. and Lau, S. L. (2022). Review on challenges and solutions in novice programming education. In 2022 IEEE International Conference on Computing (ICOCO), pages 55–61.
Speth, S., Meißner, N., and Becker, S. (2023). Investigating the use of ai-generated exercises for beginner and intermediate programming courses: A chatgpt case study. In Proceedings of the 2023 IEEE Global Engineering Education Conference (EDUCON), Vienna, Austria. IEEE.
Sweller, J. (1988). Cognitive load during problem solving: Effects on learning. Cognitive Science, 12(2):257–285.
Sweller, J., Ayres, P., and Kalyuga, S. (2011). Cognitive Load Theory. Springer, New York.
Torek, A., Sorensen, E., Hahle, N., and Kennington, C. (2024). A systematic evaluation of code-generating chatbots for use in undergraduate computer science education. In Proceedings of the 55th ACM Technical Symposium on Computer Science Education (SIGCSE), Portland, OR, USA. ACM.
Uysal, M. P. (2016). Evaluation of learning environments for object-oriented programming: measuring cognitive load with a novel measurement technique. Interactive Learning Environments, 24(7):1590–1609.
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., and Polosukhin, I. (2017). Attention is all you need. In Advances in Neural Information Processing Systems, volume 30.
Wohlin, C. (2014). Guidelines for snowballing in systematic literature studies and a replication in software engineering. In Proceedings of the 18th international conference on evaluation and assessment in software engineering, pages 1–10.
Xinogalos, S. (2015). Object-oriented design and programming: An investigation of novices’ conceptions on objects and classes. ACM Trans. Comput. Educ., 15(3).
y Fernandez, C. A. F., Sánchez-Soto, E., Cisnero, J. R. A., and Juárez-Ramírez, R. (2024). Exploring the frontier of software engineering education with chatbots. Programming and Computer Software, 50(8):796–815.
Yilmaz, R. and Yilmaz, F. G. K. (2023). Augmented intelligence in programming learning: Examining student views on the use of chatgpt for programming learning. Education and Information Technologies.
Publicado
19/07/2026
Como Citar
CAMILO, Hudson Teles; HAUCK, Jean Carlo Rossa.
Aplicações de LLMs no ensino de Programação Orientada a Objetos: Um Mapeamento Sistemático da Literatura. In: WORKSHOP SOBRE EDUCAÇÃO EM COMPUTAÇÃO (WEI), 34. , 2026, Gramado/RS.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 36-49.
ISSN 2595-6175.
DOI: https://doi.org/10.5753/wei.2026.20394.
