MEC-AI: Modelo de Enriquecimento de Explicação com Engenharia de Contexto para Inteligência Artificial
Resumo
Modelos de explicabilidade em inteligência artificial, como SHAP e LIME, apresentam limitações na compreensão do usuário por não incorporarem o contexto de uso. Este artigo apresenta o Modelo de Enriquecimento de Explicação com Engenharia de Contexto (MEC-AI), que estrutura conhecimento de domínio de forma sensível ao contexto. Fundamentado em [Bicharra 1992], o modelo amplia a XAI tradicional ao permitir explicações contextualizadas. A aplicação no mercado de trabalho baseia-se na aquisição de conhecimento com especialistas de RH e na comparação com a base da RAIS, distinguindo variáveis estruturadas daquelas que requerem complementação contextual.
Palavras-chave:
Inteligência Artificial Explicável, XAI, Engenharia de Contexto, Recursos Humanos, Sistemas Sociotécnicos
Referências
Akbari, S. and Hauswirth, M. (2024). Sampling in cloud benchmarking: A critical review and methodological guidelines. In 2024 IEEE International Conference on Cloud Computing Technology and Science (CloudCom), pages 160–167. IEEE.
Akerlof, G. A. (1978). The market for “lemons”: Quality uncertainty and the market mechanism. In Uncertainty in economics, pages 235–251. Elsevier.
Ali, S., Abuhmed, T., El-Sappagh, S., Muhammad, K., Alonso-Moral, J. M., Confalonieri, R., Guidotti, R., Del Ser, J., Díaz-Rodríguez, N., and Herrera, F. (2023). Explainable artificial intelligence (xai): What we know and what is left to attain trustworthy artificial intelligence. Information fusion, 99:101805.
Berger, L. A., Berger, D. R., and Berger, L. A. (2008). The compensation handbook, volume 5. McGraw-Hill New York.
Bertrand, A., Belloum, R., Eagan, J. R., and Maxwell, W. (2022). How cognitive biases affect xai-assisted decision-making: A systematic review. In Proceedings of the 2022 AAAI/ACM Conference on AI, Ethics, and Society, pages 78–91.
Bicharra, A. C. (1992). Active design documents: a new approach for supporting documentation in preliminary routine design.
Braun, V. and Clarke, V. (2006). Using thematic analysis in psychology. Qualitative research in psychology, 3(2):77–101.
Bujold, A., Roberge-Maltais, I., Parent-Rocheleau, X., Boasen, J., Sénécal, S., and Léger, P.-M. (2024). Responsible artificial intelligence in human resources management: a review of the empirical literature. AI and Ethics, 4(4):1185–1200.
Caccamo, M., Pittino, D., and Tell, F. (2023). Boundary objects, knowledge integration, and innovation management: A systematic review of the literature. Technovation, 122:102645.
Černevičienė, J. and Kabašinskas, A. (2024). Explainable artificial intelligence (xai) in finance: A systematic literature review. Artificial Intelligence Review, 57(8):216.
Corseuil, C. H. L., Foguel, M. N., and Gonzaga, G. (2016). A aprendizagem e a inserção de jovens no mercado de trabalho: uma análise com base na rais.
Cullen, Z., Li, S., and Perez-Truglia, R. (2025). What’s my employee worth? the effects of salary benchmarking. Review of Economic Studies, page rdaf083.
Das, S., Chakraborty, S., Sajjan, G., Majumder, S., Dey, N., and Tavares, J. M. R. (2022). Explainable ai for predictive analytics on employee attrition. In International Conference on Soft Computing and its Engineering Applications, pages 147–157. Springer.
Eichinger, F. and Mayer, M. (2022). Predicting salaries with random-forest regression. In Machine Learning and Data Analytics For Solving Business Problems: Methods, Applications, and Case Studies, pages 1–21. Springer.
Fabeyo, S. (2025). Explainable ai in employment decision-making: a systematic review of transparency methods in hiring algorithms. Issues in Information Systems, 26(3).
Fidel, G., Bitton, R., and Shabtai, A. (2020). When explainability meets adversarial learning: Detecting adversarial examples using shap signatures. In 2020 international joint conference on neural networks (IJCNN), pages 1–8. IEEE.
Hooshyar, D. and Yang, Y. (2024). Problems with shap and lime in interpretable ai for education: A comparative study of post-hoc explanations and neural-symbolic rule extraction. IEEE Access, 12:137472–137490.
Klein, H. K. and Myers, M. D. (1999). A set of principles for conducting and evaluating interpretive field studies in information systems. MIS quarterly, pages 67–93.
Lee, A. S. and Liebenau, J. (1997). Information systems and qualitative research. In Information Systems and Qualitative Research: Proceedings of the IFIP TC8 WG 8.2 International Conference on Information Systems and Qualitative Research, 31st May–3rd June 1997, Philadelphia, Pennsylvania, USA, pages 1–8. Springer.
Lundberg, S. (2017). A unified approach to interpreting model predictions. arXiv preprint arXiv:1705.07874.
Mancha, A. and Mattos, E. (2020). Public versus private wage differential in brazilian public firms. EconomiA, 21(1):1–17.
Marra, T. and Kubiak, E. (2024). Addressing diversity in hiring procedures: a generative adversarial network approach. AI and Ethics, pages 1–25.
Mei, L., Yao, J., Ge, Y., Wang, Y., Bi, B., Cai, Y., Liu, J., Li, M., Li, Z.-Z., Zhang, D., et al. (2025). A survey of context engineering for large language models. arXiv preprint arXiv:2507.13334.
Ministério do Trabalho e Emprego (2025). Relação anual de informações sociais (rais). [link]. Acesso em 28 fev. 2026.
Mohammed, A., Khalifa, G. S., and Alhammadi, F. H. (2025). Evaluating responsible ai adaption: Ethics, bias mitigation, and governance. In 2025 10th International Conference on Information Technology Trends (ITT), pages 235–240. IEEE.
Naudé, M., Adebayo, K. J., and Nanda, R. (2023). A machine learning approach to detecting fraudulent job types. AI & SOCIETY, 38(2):1013–1024.
Özer, Ş. D. İ., Ülke, B., Daniş, F. S., and Orman, G. K. (2022). Salary prediction via sectoral features in turkey. In 2022 International Conference on INnovations in Intelligent SysTems and Applications (INISTA), pages 1–6. IEEE.
Pessach, D., Singer, G., Avrahami, D., Ben-Gal, H. C., Shmueli, E., and Ben-Gal, I. (2020). Employees recruitment: A prescriptive analytics approach via machine learning and mathematical programming. Decision Support Systems, 134:113290.
Pinto, G. B. S., de Mello, C. E., and Garcia, A. C. B. (2025). Explainable ai in labor market applications. ICAART (3), pages 1450–1457.
Ribeiro, M. T., Singh, S., and Guestrin, C. (2016). ”why should i trust you?”explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pages 1135–1144.
Rigotti, C. and Fosch-Villaronga, E. (2024). Fairness, ai & recruitment. Computer Law & Security Review, 53:105966.
Sarker, S., Xiao, X., and Beaulieu, T. (2013). Guest editorial: Qualitative studies in information systems: A critical review and some guiding principles1. MIS quarterly, 37(4):ii–xviii.
Schultze, U. and Avital, M. (2011). Designing interviews to generate rich data for information systems research. Information and organization, 21(1):1–16.
Sibona, C., Walczak, S., and White Baker, E. (2020). A guide for purposive sampling on twitter. Communications of the association for information systems, 46(1):22.
Siswanto, J. V., Castilani, L. A., Winata, N. H., Nugraha, N. C., and Sagala, N. T. (2023). Salary classification & prediction based on job field and location using ensemble methods. In 2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE), pages 325–330. IEEE.
Smith, A. R., Colombi, J. M., and Wirthlin, J. R. (2013). Rapid development: A content analysis comparison of literature and purposive sampling of rapid reaction projects. Procedia Computer Science, 16:475–482.
Spence, M. (1978). Job market signaling. In Uncertainty in economics, pages 281–306. Elsevier.
Star, S. L. and Griesemer, J. R. (1989). Institutional ecology,translations’ and boundary objects: Amateurs and professionals in berkeley’s museum of vertebrate zoology, 1907-39. Social studies of science, 19(3):387–420.
Stiglitz, J. E. (1975). The theory of”screening,”education, and the distribution of income. The American economic review, 65(3):283–300.
Sun, Y., Ji, Y., Zhu, H., Zhuang, F., He, Q., and Xiong, H. (2024). Market-aware long-term job skill recommendation with explainable deep reinforcement learning. ACM Transactions on Information Systems.
Tran, H. X., Le, T. D., Li, J., Liu, L., Liu, J., Zhao, Y., and Waters, T. (2021). Recommending the most effective intervention to improve employment for job seekers with disability. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, pages 3616–3626.
Vemulapati, J., Bayyana, A., Bathula, S. H., Tokala, S., Hajarathaiah, K., and Enduri, M. K. (2023). Empirical analysis of income prediction using deep learning techniques. In 2023 IEEE International Students’ Conference on Electrical, Electronics and Computer Science (SCEECS), pages 1–6. IEEE.
Wainer, J. et al. (2007). Métodos de pesquisa quantitativa e qualitativa para a ciência da computação. Atualização em informática, 1(221-262):32–33.
Werth, O., Köhlke, J. P., and Nickerson, R. (2024). Beyond the border–a taxonomic analysis of the adoption of boundary objects in information systems research.
Zhang, Q., Zhu, H., Sun, Y., Liu, H., Zhuang, F., and Xiong, H. (2021). Talent demand forecasting with attentive neural sequential model. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, pages 3906–3916.
Akerlof, G. A. (1978). The market for “lemons”: Quality uncertainty and the market mechanism. In Uncertainty in economics, pages 235–251. Elsevier.
Ali, S., Abuhmed, T., El-Sappagh, S., Muhammad, K., Alonso-Moral, J. M., Confalonieri, R., Guidotti, R., Del Ser, J., Díaz-Rodríguez, N., and Herrera, F. (2023). Explainable artificial intelligence (xai): What we know and what is left to attain trustworthy artificial intelligence. Information fusion, 99:101805.
Berger, L. A., Berger, D. R., and Berger, L. A. (2008). The compensation handbook, volume 5. McGraw-Hill New York.
Bertrand, A., Belloum, R., Eagan, J. R., and Maxwell, W. (2022). How cognitive biases affect xai-assisted decision-making: A systematic review. In Proceedings of the 2022 AAAI/ACM Conference on AI, Ethics, and Society, pages 78–91.
Bicharra, A. C. (1992). Active design documents: a new approach for supporting documentation in preliminary routine design.
Braun, V. and Clarke, V. (2006). Using thematic analysis in psychology. Qualitative research in psychology, 3(2):77–101.
Bujold, A., Roberge-Maltais, I., Parent-Rocheleau, X., Boasen, J., Sénécal, S., and Léger, P.-M. (2024). Responsible artificial intelligence in human resources management: a review of the empirical literature. AI and Ethics, 4(4):1185–1200.
Caccamo, M., Pittino, D., and Tell, F. (2023). Boundary objects, knowledge integration, and innovation management: A systematic review of the literature. Technovation, 122:102645.
Černevičienė, J. and Kabašinskas, A. (2024). Explainable artificial intelligence (xai) in finance: A systematic literature review. Artificial Intelligence Review, 57(8):216.
Corseuil, C. H. L., Foguel, M. N., and Gonzaga, G. (2016). A aprendizagem e a inserção de jovens no mercado de trabalho: uma análise com base na rais.
Cullen, Z., Li, S., and Perez-Truglia, R. (2025). What’s my employee worth? the effects of salary benchmarking. Review of Economic Studies, page rdaf083.
Das, S., Chakraborty, S., Sajjan, G., Majumder, S., Dey, N., and Tavares, J. M. R. (2022). Explainable ai for predictive analytics on employee attrition. In International Conference on Soft Computing and its Engineering Applications, pages 147–157. Springer.
Eichinger, F. and Mayer, M. (2022). Predicting salaries with random-forest regression. In Machine Learning and Data Analytics For Solving Business Problems: Methods, Applications, and Case Studies, pages 1–21. Springer.
Fabeyo, S. (2025). Explainable ai in employment decision-making: a systematic review of transparency methods in hiring algorithms. Issues in Information Systems, 26(3).
Fidel, G., Bitton, R., and Shabtai, A. (2020). When explainability meets adversarial learning: Detecting adversarial examples using shap signatures. In 2020 international joint conference on neural networks (IJCNN), pages 1–8. IEEE.
Hooshyar, D. and Yang, Y. (2024). Problems with shap and lime in interpretable ai for education: A comparative study of post-hoc explanations and neural-symbolic rule extraction. IEEE Access, 12:137472–137490.
Klein, H. K. and Myers, M. D. (1999). A set of principles for conducting and evaluating interpretive field studies in information systems. MIS quarterly, pages 67–93.
Lee, A. S. and Liebenau, J. (1997). Information systems and qualitative research. In Information Systems and Qualitative Research: Proceedings of the IFIP TC8 WG 8.2 International Conference on Information Systems and Qualitative Research, 31st May–3rd June 1997, Philadelphia, Pennsylvania, USA, pages 1–8. Springer.
Lundberg, S. (2017). A unified approach to interpreting model predictions. arXiv preprint arXiv:1705.07874.
Mancha, A. and Mattos, E. (2020). Public versus private wage differential in brazilian public firms. EconomiA, 21(1):1–17.
Marra, T. and Kubiak, E. (2024). Addressing diversity in hiring procedures: a generative adversarial network approach. AI and Ethics, pages 1–25.
Mei, L., Yao, J., Ge, Y., Wang, Y., Bi, B., Cai, Y., Liu, J., Li, M., Li, Z.-Z., Zhang, D., et al. (2025). A survey of context engineering for large language models. arXiv preprint arXiv:2507.13334.
Ministério do Trabalho e Emprego (2025). Relação anual de informações sociais (rais). [link]. Acesso em 28 fev. 2026.
Mohammed, A., Khalifa, G. S., and Alhammadi, F. H. (2025). Evaluating responsible ai adaption: Ethics, bias mitigation, and governance. In 2025 10th International Conference on Information Technology Trends (ITT), pages 235–240. IEEE.
Naudé, M., Adebayo, K. J., and Nanda, R. (2023). A machine learning approach to detecting fraudulent job types. AI & SOCIETY, 38(2):1013–1024.
Özer, Ş. D. İ., Ülke, B., Daniş, F. S., and Orman, G. K. (2022). Salary prediction via sectoral features in turkey. In 2022 International Conference on INnovations in Intelligent SysTems and Applications (INISTA), pages 1–6. IEEE.
Pessach, D., Singer, G., Avrahami, D., Ben-Gal, H. C., Shmueli, E., and Ben-Gal, I. (2020). Employees recruitment: A prescriptive analytics approach via machine learning and mathematical programming. Decision Support Systems, 134:113290.
Pinto, G. B. S., de Mello, C. E., and Garcia, A. C. B. (2025). Explainable ai in labor market applications. ICAART (3), pages 1450–1457.
Ribeiro, M. T., Singh, S., and Guestrin, C. (2016). ”why should i trust you?”explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pages 1135–1144.
Rigotti, C. and Fosch-Villaronga, E. (2024). Fairness, ai & recruitment. Computer Law & Security Review, 53:105966.
Sarker, S., Xiao, X., and Beaulieu, T. (2013). Guest editorial: Qualitative studies in information systems: A critical review and some guiding principles1. MIS quarterly, 37(4):ii–xviii.
Schultze, U. and Avital, M. (2011). Designing interviews to generate rich data for information systems research. Information and organization, 21(1):1–16.
Sibona, C., Walczak, S., and White Baker, E. (2020). A guide for purposive sampling on twitter. Communications of the association for information systems, 46(1):22.
Siswanto, J. V., Castilani, L. A., Winata, N. H., Nugraha, N. C., and Sagala, N. T. (2023). Salary classification & prediction based on job field and location using ensemble methods. In 2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE), pages 325–330. IEEE.
Smith, A. R., Colombi, J. M., and Wirthlin, J. R. (2013). Rapid development: A content analysis comparison of literature and purposive sampling of rapid reaction projects. Procedia Computer Science, 16:475–482.
Spence, M. (1978). Job market signaling. In Uncertainty in economics, pages 281–306. Elsevier.
Star, S. L. and Griesemer, J. R. (1989). Institutional ecology,translations’ and boundary objects: Amateurs and professionals in berkeley’s museum of vertebrate zoology, 1907-39. Social studies of science, 19(3):387–420.
Stiglitz, J. E. (1975). The theory of”screening,”education, and the distribution of income. The American economic review, 65(3):283–300.
Sun, Y., Ji, Y., Zhu, H., Zhuang, F., He, Q., and Xiong, H. (2024). Market-aware long-term job skill recommendation with explainable deep reinforcement learning. ACM Transactions on Information Systems.
Tran, H. X., Le, T. D., Li, J., Liu, L., Liu, J., Zhao, Y., and Waters, T. (2021). Recommending the most effective intervention to improve employment for job seekers with disability. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, pages 3616–3626.
Vemulapati, J., Bayyana, A., Bathula, S. H., Tokala, S., Hajarathaiah, K., and Enduri, M. K. (2023). Empirical analysis of income prediction using deep learning techniques. In 2023 IEEE International Students’ Conference on Electrical, Electronics and Computer Science (SCEECS), pages 1–6. IEEE.
Wainer, J. et al. (2007). Métodos de pesquisa quantitativa e qualitativa para a ciência da computação. Atualização em informática, 1(221-262):32–33.
Werth, O., Köhlke, J. P., and Nickerson, R. (2024). Beyond the border–a taxonomic analysis of the adoption of boundary objects in information systems research.
Zhang, Q., Zhu, H., Sun, Y., Liu, H., Zhuang, F., and Xiong, H. (2021). Talent demand forecasting with attentive neural sequential model. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, pages 3906–3916.
Publicado
08/06/2026
Como Citar
PINTO, Gabriel Bicharra Santini; GARCIA, Ana Cristina Bicharra.
MEC-AI: Modelo de Enriquecimento de Explicação com Engenharia de Contexto para Inteligência Artificial. In: SIMPÓSIO BRASILEIRO DE SISTEMAS COLABORATIVOS (SBSC), 21. , 2026, Porto Alegre/RS.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 484-494.
ISSN 2326-2842.
DOI: https://doi.org/10.5753/sbsc.2026.20924.
