Engenharia de Requisitos de Explicabilidade em Sistemas Baseados em Aprendizado de Máquina
Resumo
A explicabilidade e a habilidade de tornar as previsões de um modelo de Aprendizado de Maquina (AM) claras e compreensíveis para as pessoas. A adoção de modelos de AM em decisões críticas exige que a explicabilidade seja incorporada como um requisito fundamental no processo de tomada de decisão. Por ser um tema recente, a explicabilidade em sistemas baseados em AM ainda carece de processos sistematizados, o que abre espaço para novas pesquisas. Este trabalho de doutorado visa desenvolver e contribuir com uma abordagem de Engenharia de Requisitos para analise e especificação de requisitos de explicabilidade em sistemas baseados em AM. A metodologia Design Science servirá de modelo para conduzir esta pesquisa.
Palavras-chave:
engenharia de requisitos, explicabilidade, aprendizado de máquina
Referências
Baldassarre, M. T., Gigante, D., Kalinowski, M., Ragone, A., and Tibidò, S. (2024). Trustworthy ai in practice: an analysis of practitioners’ needs and challenges. In Proceedings of the 28th International Conference on Evaluation and Assessment in Software Engineering, pages 293–302.
Barrera, J. M., Reina-Reina, A., Lavalle, A., Maté, A., and Trujillo, J. (2024). An extension of istar for machine learning requirements by following the prise methodology. Computer Standards & Interfaces, 88:103806.
Bogucka, E., Constantinides, M., Scepanovic, S., and Quercia, D. (2024). Ai design: A responsible ai framework for pre-filling impact assessment reports. IEEE Computer Society.
Chazette, L., Brunotte, W., and Speith, T. (2022). Explainable software systems: from requirements analysis to system evaluation. Requirements Engineering, 27(4):457–487.
Clement, T., Kemmerzell, N., Abdelaal, M., and Amberg, M. (2023). Xair: A systematic metareview of explainable ai (xai) aligned to the software development process. Machine Learning and Knowledge Extraction, 5(1):78–108.
Engström, E., Storey, M.-A., Runeson, P., Höst, M., and Baldassarre, M. T. (2020). How software engineering research aligns with design science: a review. Empirical Software Engineering, 25:2630–2660.
Giray, G. (2021). A software engineering perspective on engineering machine learning systems: State of the art and challenges. Journal of Systems and Software, 180:111031.
Goodell, J. W. et al. (2021). Artificial intelligence and machine learning in finance: Identifying foundations, themes, and research clusters from bibliometric analysis. Journal of Behavioral and Experimental Finance, 32:100577.
Guizzardi, R., Amaral, G., Guizzardi, G., and Mylopoulos, J. (2022). Eliciting ethicality requirements using the ontology-based requirements engineering method. In International Conference on Business Process Modeling, Development and Support, pages 221–236. Springer.
Habibullah, K. M. et al. (2024). Explainable ai: A diverse stakeholder perspective. In 2024 IEEE 32nd International Requirements Engineering Conference (RE), pages 494–495. IEEE.
Jiang, F. et al. (2017). Artificial intelligence in healthcare: past, present and future. Stroke and vascular neurology, 2(4).
Khattak, F. K., Subasri, V., Krishnan, A., Pou-Prom, C., Akinli-Kocak, S., Dolatabadi, E., Pandya, D., Seyyed-Kalantari, L., and Rudzicz, F. (2024). Mlhops: Machine learning health operations. IEEE Access.
Li, T. and Han, L. (2023). Dealing with explainability requirements for machine learning systems. In 2023 IEEE 47th Annual Computers, Software, and Applications Conference (COMPSAC), pages 1203–1208. IEEE.
Lin, H., Han, J., Wu, P., Wang, J., Tu, J., Tang, H., and Zhu, L. (2024). Machine learning and human-machine trust in healthcare: A systematic survey. CAAI Transactions on Intelligence Technology, 9(2):286–302.
Mancine, L., Soares, J. L., Kudo, T., and Bulcão-Neto, R. (2024). Estado da arte sobre engenharia de requisitos e explicabilidade em sistemas baseados em aprendizado de máquina. In Anais Estendidos do XXX Simpósio Brasileiro de Sistemas Multimídia e Web, pages 143–158, Porto Alegre, RS, Brasil. SBC.
Martins, M. C., Campos, L. M. C., Soares, J. L. R., Kudo, T. N., and Bulcão-Neto, R. F. (2025). Requirements engineering for machine learning-based ai systems: A tertiary study. Journal of Software Engineering Research and Development (JSERD). Submitted and under review.
Senado Federal do Brasil (2023). Projeto de Lei Nº 2338, de 2023. Disponível em: [link]. Acesso em: 28 jan. 2025.
Storey, M.-A., Engstrom, E., Höst, M., Runeson, P., and Bjarnason, E. (2017). Using a visual abstract as a lens for communicating and promoting design science research in software engineering. In 2017 ACM/IEEE International Symposium on Empirical Software Engineering and Measurement (ESEM), pages 181–186. IEEE.
Umm-E-Habiba (2023). Requirements engineering for explainable ai. In 2023 IEEE 31st International Requirements Engineering Conference (RE), pages 376–380.
Vayena, E., Blasimme, A., and Cohen, I. G. (2018). Machine learning in medicine: addressing ethical challenges. PLoS medicine, 15(11):e1002689.
Villamizar, H., Kalinowski, M., Lopes, H., and Mendez, D. (2024). Identifying concerns when specifying machine learning-enabled systems: a perspective-based approach. Journal of Systems and Software, 213:112053.
Barrera, J. M., Reina-Reina, A., Lavalle, A., Maté, A., and Trujillo, J. (2024). An extension of istar for machine learning requirements by following the prise methodology. Computer Standards & Interfaces, 88:103806.
Bogucka, E., Constantinides, M., Scepanovic, S., and Quercia, D. (2024). Ai design: A responsible ai framework for pre-filling impact assessment reports. IEEE Computer Society.
Chazette, L., Brunotte, W., and Speith, T. (2022). Explainable software systems: from requirements analysis to system evaluation. Requirements Engineering, 27(4):457–487.
Clement, T., Kemmerzell, N., Abdelaal, M., and Amberg, M. (2023). Xair: A systematic metareview of explainable ai (xai) aligned to the software development process. Machine Learning and Knowledge Extraction, 5(1):78–108.
Engström, E., Storey, M.-A., Runeson, P., Höst, M., and Baldassarre, M. T. (2020). How software engineering research aligns with design science: a review. Empirical Software Engineering, 25:2630–2660.
Giray, G. (2021). A software engineering perspective on engineering machine learning systems: State of the art and challenges. Journal of Systems and Software, 180:111031.
Goodell, J. W. et al. (2021). Artificial intelligence and machine learning in finance: Identifying foundations, themes, and research clusters from bibliometric analysis. Journal of Behavioral and Experimental Finance, 32:100577.
Guizzardi, R., Amaral, G., Guizzardi, G., and Mylopoulos, J. (2022). Eliciting ethicality requirements using the ontology-based requirements engineering method. In International Conference on Business Process Modeling, Development and Support, pages 221–236. Springer.
Habibullah, K. M. et al. (2024). Explainable ai: A diverse stakeholder perspective. In 2024 IEEE 32nd International Requirements Engineering Conference (RE), pages 494–495. IEEE.
Jiang, F. et al. (2017). Artificial intelligence in healthcare: past, present and future. Stroke and vascular neurology, 2(4).
Khattak, F. K., Subasri, V., Krishnan, A., Pou-Prom, C., Akinli-Kocak, S., Dolatabadi, E., Pandya, D., Seyyed-Kalantari, L., and Rudzicz, F. (2024). Mlhops: Machine learning health operations. IEEE Access.
Li, T. and Han, L. (2023). Dealing with explainability requirements for machine learning systems. In 2023 IEEE 47th Annual Computers, Software, and Applications Conference (COMPSAC), pages 1203–1208. IEEE.
Lin, H., Han, J., Wu, P., Wang, J., Tu, J., Tang, H., and Zhu, L. (2024). Machine learning and human-machine trust in healthcare: A systematic survey. CAAI Transactions on Intelligence Technology, 9(2):286–302.
Mancine, L., Soares, J. L., Kudo, T., and Bulcão-Neto, R. (2024). Estado da arte sobre engenharia de requisitos e explicabilidade em sistemas baseados em aprendizado de máquina. In Anais Estendidos do XXX Simpósio Brasileiro de Sistemas Multimídia e Web, pages 143–158, Porto Alegre, RS, Brasil. SBC.
Martins, M. C., Campos, L. M. C., Soares, J. L. R., Kudo, T. N., and Bulcão-Neto, R. F. (2025). Requirements engineering for machine learning-based ai systems: A tertiary study. Journal of Software Engineering Research and Development (JSERD). Submitted and under review.
Senado Federal do Brasil (2023). Projeto de Lei Nº 2338, de 2023. Disponível em: [link]. Acesso em: 28 jan. 2025.
Storey, M.-A., Engstrom, E., Höst, M., Runeson, P., and Bjarnason, E. (2017). Using a visual abstract as a lens for communicating and promoting design science research in software engineering. In 2017 ACM/IEEE International Symposium on Empirical Software Engineering and Measurement (ESEM), pages 181–186. IEEE.
Umm-E-Habiba (2023). Requirements engineering for explainable ai. In 2023 IEEE 31st International Requirements Engineering Conference (RE), pages 376–380.
Vayena, E., Blasimme, A., and Cohen, I. G. (2018). Machine learning in medicine: addressing ethical challenges. PLoS medicine, 15(11):e1002689.
Villamizar, H., Kalinowski, M., Lopes, H., and Mendez, D. (2024). Identifying concerns when specifying machine learning-enabled systems: a perspective-based approach. Journal of Systems and Software, 213:112053.
Publicado
12/05/2025
Como Citar
MANCINE, Lívia.
Engenharia de Requisitos de Explicabilidade em Sistemas Baseados em Aprendizado de Máquina. In: CONGRESSO IBERO-AMERICANO EM ENGENHARIA DE SOFTWARE (CIBSE), 28. , 2025, Ciudad Real/Espanha.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 296-303.
DOI: https://doi.org/10.5753/cibse.2025.35316.
