THE EVOLUTION OF EXPLAINABLE ARTIFICIAL INTELLIGENCE (XAI)
DOI:
https://doi.org/10.47820/recima21.v7i3.7438Keywords:
Explainable Artificial Intelligence, XAI, Model Interpretability, Algorithmic Transparency, Bibliometrics.Abstract
This article analyzes the evolution of Artificial Intelligence (AI) up to the consolidation of Explainable Artificial Intelligence (XAI), emphasizing how the advancement of machine learning and, above all, deep learning has increased the performance of models at the cost of greater opacity ("black box"). The literature review shows that explainability became essential as AI systems were adopted in high-stakes domains (healthcare, finance, justice, and security), where automated decisions affect rights and require trust, auditability, and accountability. Key XAI milestones include post-hoc explanation methods such as LIME and SHAP and conceptual frameworks that distinguish interpretability and explainability. Methodologically, the study combines a narrative literature review, bibliographic and documentary analysis (including regulatory discussions related to the GDPR), and bibliometric analysis. Results based on bibliometric evidence (Scopus, 2004–2023) indicate rapid growth of XAI publications from 2018 onwards, identifying leading authors and major publication venues (journals and proceedings series). In addition, Google Trends suggests rising public interest in “explainable artificial intelligence,” while also revealing semantic ambiguity around the term “XAI” in web searches, which can bias query-based analyzes unless carefully controlled. Overall, XAI emerges as a technical and socio-technical response to model complexity and to ethical and regulatory demands for transparency.
Downloads
References
ALVES, Davis Souza; LIMA, Adrianne Correia. Encarregados: Data Protection Officer (DPO). [S. l.]: Editora Haikai, 2021.
ARRIETA, Alejandro Barredo et al. Explainable artificial intelligence (XAI): concepts, taxonomies, opportunities and challenges toward responsible AI. Information Fusion, v. 58, p. 82–115, 2020.
BAROCAS, Solon; SELBST, Andrew D. Big data’s disparate impact. California Law Review, Berkeley, v. 104, n. 3, p. 671–732, 2016.
BISHOP, Christopher M. Pattern recognition and machine learning. New York: Springer, 2006.
COMISSÃO EUROPEIA. Ethics guidelines for trustworthy AI. Bruxelas: European Commission, 2019.
DOSHI-VELEZ, Finale; KIM, Been. Towards a rigorous science of interpretable machine learning. arXiv preprint, arXiv:1702.08608, 2017.
GOODFELLOW, Ian; BENGIO, Yoshua; COURVILLE, Aaron. Deep learning. Cambridge: MIT Press, 2016.
GOODFELLOW, Ian; SHLENS, Jonathon; SZEGEDY, Christian. Explaining and harnessing adversarial examples. arXiv preprint, 2015.
GOOGLE TRENDS. Inteligência artificial explicável (assunto). Escopo: global; intervalo: últimos cinco anos; tipo: Pesquisa Google na Web. Acesso em: 18 fev. 2026.
GOV.UK. Data ethics framework. London: Government Digital Service, 2018. Atualizado em 2025.
GUNNING, David. Explainable artificial intelligence (XAI). Arlington: DARPA, 2017.
ICO – INFORMATION COMMISSIONER’S OFFICE. Explaining decisions made with AI. London: ICO, 2020.
LECUN, Yann; BENGIO, Yoshua; HINTON, Geoffrey. Deep learning. Nature, London, v. 521, p. 436–444, 2015.
LIPTON, Zachary C. The mythos of model interpretability. Communications of the ACM, v. 61, n. 10, p. 36–43, 2018.
LUNDBERG, Scott M.; LEE, Su-In. A unified approach to interpreting model predictions. In: Advances in Neural Information Processing Systems (NeurIPS), 2017.
MOLNAR, Christoph. Interpretable machine learning. 2. ed. [S. l.]: Leanpub, 2022.
NILSSON, Nils J. The quest for artificial intelligence: a history of ideas and achievements. Cambridge: Cambridge University Press, 2010.
RIBEIRO, Marco Tulio; SINGH, Sameer; GUESTRIN, Carlos. “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. New York: ACM, 2016. p. 1135–1144.
RUSSELL, Stuart; NORVIG, Peter. Artificial intelligence: a modern approach. 3. ed. Upper Saddle River: Pearson, 2016.
SHARMA, Chetan et al. Exploring explainable AI: a bibliometric analysis. Discover Applied Sciences, v. 6, 2024.
WACHTER, Sandra; MITTELSTADT, Brent; FLORIDI, Luciano. Why a right to explanation of automated decision-making does not exist in the General Data Protection Regulation. International Data Privacy Law, Oxford, v. 7, n. 2, p. 76–99, 2017.
ZHOU, Zhi-Hua et al. Machine learning in China: past, present and future. National Science Review, Oxford, v. 6, n. 1, p. 19–38, 2019.
Downloads
Published
Issue
Section
Categories
License
Copyright (c) 2026 RECIMA21 - Revista Científica Multidisciplinar - ISSN 2675-6218
This work is licensed under a Creative Commons Attribution 4.0 International License.
Os direitos autorais dos artigos/resenhas/TCCs publicados pertecem à revista RECIMA21, e seguem o padrão Creative Commons (CC BY 4.0), permitindo a cópia ou reprodução, desde que cite a fonte e respeite os direitos dos autores e contenham menção aos mesmos nos créditos. Toda e qualquer obra publicada na revista, seu conteúdo é de responsabilidade dos autores, cabendo a RECIMA21 apenas ser o veículo de divulgação, seguindo os padrões nacionais e internacionais de publicação.
