SAGAR: Artificial Intelligence-Based System for Supporting the Automatic Generation of Summaries as a Pedagogical Tool for Teachers
DOI:
https://doi.org/10.22481/recic.v8i1.19821Keywords:
Artificial Intelligence, Natural Language Processing, Automatic Speech Recognition, Text Summarization, Educational Technology.Abstract
This study presents SAGAR (System for Supporting Automatic Summary Generation), an Artificial Intelligence-based solution designed to support teachers in the automatic production of structured summaries from lecture-based classes. The system integrates Automatic Speech Recognition and Natural Language Processing techniques into a pipeline comprising audio capture, temporal segmentation, transcription, partial summarization, and aggregation, with the aim of reducing the effort required for manual preparation of post-class educational materials. The platform is intended for teacher use, and the generated summaries may be shared with students through channels external to the system. The initial evaluation was internal, exploratory, and preliminary, and was conducted by the authors in four controlled scenarios, considering three dimensions: summary coherence, transcription integrity, and functional consistency. The first two dimensions were assessed using a five-point ordinal scale, with all outputs receiving the maximum score of 5.0, whereas functional consistency was examined across five stages of the pipeline. A total of 20 functional checks were performed, all completed without observable failures, corresponding to a descriptive execution rate of 100% in the analyzed scenarios. These findings should be interpreted solely as preliminary evidence of system operation under controlled conditions, since the evaluation did not involve blinding, independent evaluators, real users, or inter-rater agreement measures. As a future step, the project will be submitted to a Research Ethics Committee to enable external evaluation with human participants in real educational settings.
Downloads
References
I. D. Mienye and T. G. Swart, “A comprehensive review of deep learning: Architectures, recent advances, and applications,” Information, vol. 15, no. 12, p. 755, 2024.
A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin, “Attention is all you need,” Advances in Neural Information Processing Systems, vol. 30, 2017.
J. Garzon, E. Patiño, and C. Marulanda, “Systematic review of artificial intelligence in education: Trends, benefits, and challenges,” Multimodal Technologies and Interaction, vol. 9, no. 8, p. 84, 2025.
M. Y. Mustafa, A. Tlili, G. Lampropoulos, R. Huang, P. Jandrić, J. Zhao, S. Salha, L. Xu, S. Panda, Kinshuk, et al., “A systematic review of literature reviews on artificial intelligence in education (AIED): A roadmap to a future research agenda,” Smart Learning Environments, vol. 11, no. 1, p. 59, 2024.
D. Zhao, “The impact of AI-enhanced natural language processing tools on writing proficiency: An analysis of language precision, content summarization, and creative writing facilitation,” Education and Information Technologies, vol. 30, no. 6, pp. 8055–8086, 2025.
C. R. d. A. C. Barbosa, “Transformações no ensino-aprendizagem com o uso da inteligência artificial: Revisão sistemática da literatura,” RECIMA21 — Revista Científica Multidisciplinar, vol. 4, no. 5, pp. e453103–e453103, 2023.
I. M. de Vasconcelos, A. J. R. Ambrozio, A. B. B. Almeida, R. A. C. da Silva, G. B. de Sá, M. C. V. Segura, R. Walter, and A. A. G. R. de Oliveira, “O papel da inteligência artificial na educação: Ferramenta de suporte ou substituta?,” Lumen et Virtus, vol. 15, no. 43, pp. 7918–7933, 2024.
N. Kala and A. Ayas, “Effect of instructional design based on cognitive load theory on students’ performances and the indicators of element interactivity,” Journal of Turkish Science Education, vol. 20, no. 3, pp. 468–489, 2023.
I. I. Salame, M. Tuba, and M. Nujhat, “Note-taking and its impact on learning, academic performance, and memory,” International Journal of Instruction, vol. 17, no. 3, pp. 599–616, 2024.
X. Tan, G. Cheng, and M. H. Ling, “Artificial intelligence in teaching and teacher professional development: A systematic review,” Computers and Education: Artificial Intelligence, vol. 8, p. 100355, 2025.
H. C. Araujo, M. O. Lisboa, P. H. C. Pereira, I. d. C. Freitas, M. L. B. Villela, and R. Ferreira, “Desenvolvimento de ferramentas educacionais para computação com apoio de modelos generativos de linguagem,” Revista Brasileira de Informática na Educação, vol. 34, pp. 279–313, mar. 2026.
J. M. Akazaki, L. S. R. Machado, and P. A. Behar, “MOSALA: Modelo socioafetivo baseado em Learning Analytics para auxiliar professores no acompanhamento de estudantes em um ambiente virtual de aprendizagem,” Revista Brasileira de Informática na Educação, vol. 34, pp. 598–625, may 2026.
R. Ranchal, T. Taber-Doughty, Y. Guo, K. Bain, H. Martin, J. P. Robinson, and B. S. Duerstock, “Using speech recognition for real-time captioning and lecture transcription in the classroom,” IEEE Transactions on Learning Technologies, vol. 6, no. 4, pp. 299–311, 2013.
A. Aher, R. Sawant, R. Patil, S. Sabat, and T. Panchal, “Mindscape: An AI-powered study companion integrating natural language processing algorithms,” in 2025 3rd International Conference on Communication, Security, and Artificial Intelligence (ICCSAI), vol. 3, pp. 2116–2121, IEEE, 2025.
E. L. Ecker, L. W. Costa, and L. M. O. de Barros Cardoso, “Uso da lousa digital em sala de aula: Benefícios e desafios,” Revista Ibero-Americana de Humanidades, Ciências e Educação, vol. 11, no. 6, pp. 1997–2006, 2025.
I. Yamamoto and V. B. Barbeta, “Simulações de experiências como ferramenta de demonstração virtual em aulas de teoria de física,” Revista Brasileira de Ensino de Física, vol. 23, pp. 215–225, 2001.
A. da Silva Pereira and A. F. Seoane, “A adequação das legendas automáticas do aplicativo CapCut em vídeos verticais para legendagem para surdos e ensurdecidos,” Revista Linguagem em Foco, vol. 17, no. 3, pp. 168–187, 2025.
A. J. S. d. Souza, A. B. Possato, J. P. Curtulo, D. R. d. Silva, A. C. d. Santos, T. Ferla, M. E. d. Oliveira Junior, and E. H. d. S. Gonçalves, “IA na educação: Tendências e desafios recentes,” Cuadernos de Educación y Desarrollo, vol. 17, no. 5, pp. 1–18, 2025.
D. M. A. d. A. Pestana dos Santos, “Inteligência artificial na educação contemporânea,” Revista Processando o Saber, vol. 17, pp. 51–73, 2025.
C. C. d. Azambuja and G. Ferreira da Silva, “Novos desafios para a educação na era da inteligência artificial,” Filosofia Unisinos, vol. 25, no. 1, pp. 1–16, 2024.
L. Qin et al., “Large language models meet NLP: A survey,” Frontiers of Computer Science, vol. 0, no. 0, pp. 1–35, 2025.
M. M. R. Silva, “Sumarização automática de textos: Desafios e avanços em técnicas de processamento de linguagem natural,” 2023. Trabalho de Conclusão de Curso em Engenharia de Computação.
A. Nenkova and K. McKeown, “A survey of text summarization techniques,” in Mining Text Data, pp. 43–76, Springer, 2012.
M. Zhang, G. Zhou, W. Yu, N. Huang, and W. Liu, “A comprehensive survey of abstractive text summarization based on deep learning,” Computational Intelligence and Neuroscience, vol. 2022, p. 7132226, 2022.
J. Lei et al., “A survey of automatic text summarization with large language model-based methods,” arXiv preprint arXiv , 2025. Survey on ATS and LLM-based summarization methods.
H. P. Luhn, “The automatic creation of literature abstracts,” IBM Journal of Research and Development, vol. 2, pp. 159–165, Apr. 1958.
L. Sodré and H. de Oliveira, “Avaliando algoritmos de regressão para sumarização automática de textos em português do Brasil,” in Anais do XVI Encontro Nacional de Inteligência Artificial e Computacional, pp. 634–645, SBC, 2019.
P. H. Paiola, G. L. Garcia, D. S. Jodas, J. V. M. Correia, L. A. Sugi, and J. P. Papa, “Recognasumm: A novel Brazilian summarization dataset,” in Proceedings of the 16th International Conference on Computational Processing of Portuguese, pp. 575–579, 2024.
T. Zhang, V. Kishore, F. Wu, K. Q. Weinberger, and Y. Artzi, “BERTScore: Evaluating text generation with BERT,” arXiv preprint arXiv:1904.09675, 2019.
F. O. Runstein, Sistema de reconhecimento de fala baseado em redes neurais artificiais. PhD thesis, University of Campinas, Brazil, 1998.
H. Kheddar, M. Hemis, and Y. Himeur, “Automatic speech recognition using advanced deep learning approaches: A survey,” Information Fusion, vol. 109, p. 102422, 2024.
A. Radford, J. W. Kim, T. Xu, G. Brockman, C. McLeavey, and I. Sutskever, “Robust speech recognition via large-scale weak supervision,” in Proceedings of the 40th International Conference on Machine Learning, vol. 202, pp. 28492–28518, PMLR, 2023.
M. Bain, J. Huh, T. Han, and A. Zisserman, “Whisperx: Time-accurate speech transcription of long-form audio,” in Proceedings of INTERSPEECH 2023, pp. 4489–4493, 2023.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Journal of Computer Science

This work is licensed under a Creative Commons Attribution 4.0 International License.