Controlled Vocabulary and Artificial Intelligence in Indexing
A Literature Review
Keywords:
Artificial Intelligence, Librarians, Manual indexing, Automatic indexing, Information representation and retrieval, LibrariesAbstract
With artificial intelligence, librarians have found an ally in indexing to organize vast data sets. With the question: how can artificial intelligence help librarians with indexing? – the goal is to understand the relationship between artificial intelligence and indexing. A qualitative approach was adopted in bibliographic research which, after inclusion criteria (title, abstract, keywords, and thematic relevance) and exclusion criteria (duplicates and articles without full access), analyzed 27 articles (17 WoS; 10 EBSCO). It was found that: (i) artificial intelligence and/or automatic indexing do not replace librarians, but function as support; (ii) automatic indexing has evolved positively with gains in accuracy and consistency; (iii) there are effective tools applied in libraries, such as Annif, FintoAI, and Kratt; (iv) these tools play an important role in the modernization of library processes; and (v) it is inevitable that libraries will invest in continuing education and the implementation of AI solutions. The use of artificial intelligence in indexing represents a strategic opportunity for the efficiency and quality of library services. The impact of AI brings indexing closer to the natural language of users, preserving the role of the librarian and expanding their role in information management.
References
APPLETON, L. AI and academic libraries: what’s all the fuss about? New Review of Academic Librarianship, [s.l.], v. 30, n. 3-4, p. 281-295, 2024. DOI https://doi.org/10.1080/13614533.2024.2356474.
ASULA, M. et al. Kratt: developing an automatic subject indexing tool for the National Library of Estonia. Cataloguing e Classification Quarterly, [s.l.], v. 59, n. 8, p. 775-793, 2021. DOI https://doi.org/10.1080/01639374.2021.1998283.
BIBLIOTECARIA. Avanzando en la intersección de la tecnología y el conocimiento. [s.l.]: BibliotecarIA, ([2025]). Disponível em: https://www.bibliotecaria.es/. Acesso em: 31 out. 2025.
CHANDRASHEKARA, G. S.; MULIMANI, M. The impact of artificial intelligence on library and information science (LIS) services. International Journal of Innovative Practice and Applied Research (IJIPAR), [s.l.], v. 14, n. 5, p. 50-56, 2024. DOI http://dx.doi.org/10.2139/ssrn.4856459v.
CHEN, E.; BULLARD, J.; GIUSTANI, D. Automated indexing using NLM’s Medical Text Indexer (MTI) compared to human indexing in Medline: a pilot study. Journal of the Medical Library Association, Chicago, v. 111, n. 3, p. 684-694, 2023. DOI https://dx.doi.org/10.5195/jmla.2023.1588.
CHU, H. Information Representation and Retrieval in the Digital Age. 2. ed. Medford: American Society for Information Science and Technology : Information Today, 2010.
GIL-LEIVA, I. et al. Extracción de información de documentos PDF para su uso en la indización automática de e-books. Transinformação, Campinas, v. 34, [s.n.], p.1-11, 2022. DOI https://doi.org/10.1590/2318-0889202234e210069.
GOLUB, K. Potential and challenges of subject access in libraries today on the example of swedish libraries. International Information e Library Review, [s.l.], v. 48, n. 3, p. 204-210, 2016. DOI https://doi.org/10.1080/10572317.2016.1205406.
FERREIRA, M. H. W.; CORREA, R. F. Sistematização da obtenção de indicadores temáticos de informação científica. Encontros Bibli, Florianópolis, v. 28, [s.l.], p. 1-30, 2023. DOI https://doi.org/10.5007/1518-2924.2023.e92070.
KASPRZIK, A. Automatic subject indexing at ZBW: making research results stick in practice. Journal of the Association of European Research Libraries, [s.l.], v. 33, n. 1, p. 1-17, 2023. DOI https://doi.org/10.53377/lq.13579.
KING, S. et al. Revisiting indexing and abstracting in the digital era. Texas: University of North Texas, 2018. Disponível em: https://digital.library.unt.edu/ark:/67531/metadc1164546/m2/1/high_res_d/Revisiting_Indexing_and_Abstracting_in_the_Digital_Era.pdf. Acesso em: 31 out. 2025.
LLORÉNS, J. et al. Automatic generation of domain representations using thesaurus structures. Journal of the American Society for Information Science and Technology, [s.l.], v. 55, n. 10, p. 846-858, 2004. DOI https://doi.org/10.1002/asi.20039.
MANNHEIMER, S. Responsible AI practice in libraries and archives. Information Technology and Libraries, Ann Arbor, v. 43, n. 2, p. 1-20, 2024. Disponível em: https://ital.corejournals.org/index.php/ital/article/view/17245. Acesso em: 31 out. 2025.
NIRUDI, Y.; PARICHI, R. Artificial intelligence in libraries: an overview. SSRN Electronic Journal, [s.l.], [s.n.], [s.n.], nov. 2024. Disponível em: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5080670. Acesso em: 31 out. 2025.
OBASEKI, T. I. Automated indexing: the key to information retrieval in the 21st century. Library Philosophy and Practice, Nebraska, v. 338, [s.n.], p. 1-4, 2010. Disponível em: https://abrir.link/CMYCh. Acesso em: 31 out. 2025.
OLIVEIRA, R. O uso da inteligência artificial em bibliotecas universitárias: aplicações em catalogação e indexação. Porto Alegre: UFRGS, 2024. Dissertação (Mestrado em Ciência da Informação) – Universidade Federal do Rio Grande do Sul, Porto Alegre. Disponível em: https://lume.ufrgs.br/bitstream/handle/10183/290598/001244292.pdf. Acesso em: 31 out. 2025.
PARK, J.; BRENZA, A. Evaluation of semi-automatic metadata generation tools: a survey of the current state of the art. Information Technology and Libraries, Ann Arbor, v. 34, n. 3, p. 22-42, 2015. DOI https://doi.org/10.6017/ital.v34i3.5889.
PITTKE, F.; LEOPOLD, H; MENDLING, J. Automatic detection and resolution of lexical ambiguity in process models. IEEE Transactions on Software Engineering, [s.l.], v. 41, n. 6, p. 526-544, 2015. DOI https://doi.org/10.1109/TSE.2015.2396895.
STEIGER, K. Artificial Intelligence in higher education and academic libraries: a literature review. Endnotes, [s.l.], v. 125, n. 1, p. 1-15, 2024. Disponível em: https://journals.ala.org/index.php/endnotes/article/view/8235. Acesso em: 31 out. 2025.
SUOMINEN, O. Supporting subject librarians with AI solutions. Finland: IFLA, 2022. Disponível em: https://www.ifla.org/wp-content/uploads/1.Suominen_Supporting-Subject-Librarians-_-IFLA-AI-webinar.pdf. Acesso em: 31 out. 2025.
SUOMINEN, O.; INKINEN, J.; LEHTINEN, M. Annif and Finto AI: developing and implementing automated subject indexing. JLIS.it, [s.l.], v. 13, n. 1, p. 265-282, 2022. DOI https://doi.org/10.4403/jlis.it-12740.
TOEPFER, M.; SEIFERT, C. Descriptor-invariant fusion architectures for automatic subject indexing. ACM/IEEE Joint Conference on Digital Libraries (JCDL), 1., 2017, Toronto. Proceedings […]. Toronto: ACM : IEEE, 2017. p. 1-10. DOI 10.1109/JCDL.2017.7991557.
TRINDADE, Alessandra Stefane Cândido Elias da; OLIVEIRA, Henry Poncio Cruz de. Inteligência Artificial (IA) Generativa e Competência em Informação: habilidades informacionais necessárias ao uso de ferramentas de ia generativa em demandas informacionais de natureza acadêmica-científica. Perspectivas em Ciência da Informação, Belo Horizonte, v. 29, n. 2, p. 201-219, 2024. DOI http://dx.doi.org/10.1590/1981-5344/47485.
VALLEZ, M. et al. Updating controlled vocabularies by analysing query logs. Online Information Review, [s.l.], v. 39, n. 7, p. 1-24, 2015. DOI http://dx.doi.org/10.1108/OIR-06-2015-0180.
Published
Issue
Section
License
Copyright (c) 2025 Perspectivas em Ciência da Informação

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