Automatic Classification of Subjects and Sustainable Development Goals (SDGs) in Documents with Generative AI
An Experience from the Unicamp Library System
DOI:
https://doi.org/10.5860/ital.v45i1.17510Keywords:
Generative artificial intelligence, Automatic Classification, Academic Library, UN Sustainable Development Goals (SDGs)Abstract
This study evaluates the effectiveness of the Artificial Intelligence for Theme Generation tool (original Portuguese acronym name: IAGeraTemas), developed with generative artificial intelligence (AI; Google Gemini), for automating thematic classification and the assignment of Sustainable Development Goals (SDGs) in documents. The methodology combined quantitative analyses (metrics of precision, recall, and accuracy) on 50 articles published by authors from the State University of Campinas (Unicamp), using classification from the SciVal database and qualitative analyses (analysis of the relevance of terms indexed by librarians from the Unicamp Library System in 40 articles available in the Unicamp Institutional Repository), comparing them with manual indexing performed by librarians. The quantitative results in SDG classification showed a recall of 0.785, while the “precision” and “accuracy” metrics were moderate. The qualitative analysis deepened the evaluation of term coherence and relevance suggested by the AI versus human indexing. It revealed the tool’s potential for suggesting relevant terms and expanding concepts, but it also exposed limitations in addressing complex topics. The research, conducted as an experiment at Unicamp Library System, concludes that IAGeraTemas is a valuable auxiliary tool, complementing but not replacing manual indexing, reinforcing the importance of human expertise in validating and refining results, and emphasizing the synergistic potential between AI and information professionals.
References
“IFLA Statement on Libraries and Artificial Intelligence,” IFLA, 2020, https://repository.ifla.org/handle/20.500.14598/1646.
A. C. S. Santos et al., “A Literacia Digital nas Práticas Arquivísticas: Uma Revisão da Literatura,” Cuadernos de Educación y Desarrollo 15, no. 10 (2023): 12522–45, https://doi.org/10.55905/cuadv15n10-133.
A. O. Isiaka et al., “Perceived Awareness and Usefulness of Artificial Intelligence Technology for Efficient Library Operations in University Libraries in Kwara State, Nigeria,” Journal of Library Services and Technologies 6, no. 1 (2024): 120–34, https://credence-publishing.com/journal/uploads/archive/202417141644679010325466.pdf.
A. Tella, “Robots Are Coming to the Libraries: Are Librarians Ready to Accommodate Them?” Library Hi Tech News 9 (2020): 13–17, http://doi.org/10.47524/jlst.v6i1.1217.
Alexander Bedard-Vallee, Chris James, and Guillaume Roberge, “Sustainable Development Goals (SDGs) Mapping,” Elsevier Data Repository, v. 1, July 13, 2023, https://doi.org/10.17632/y2zyy9vwzy.1.
C. Halaychik. “Embrace AI in Libraries: Freeing Staff for Meaningful Work While Preserving Human Touch,” IFLA Academic and Research Libraries Section Blog, July 24, 2024, https://blogs.ifla.org/arl/2024/07/24/embrace-ai-in-libraries-freeing-staff-for-meaningful-work-while-preserving-human-touch/.
Caio Saraiva Coneglian et al., “Inteligência Artificial Generativa e Recuperação da Informação: Tendências e Oportunidades de Pesquisa,” in Anais do 23. Encontro Nacional de Pesquisa em Ciência da Informação, 1–16 (ANCIB, 2023), https://ancib.org/enancib/index.php/enancib/xxxiiienancib/paper/view/1944.
Cristina Arhiliuc, Raf Guns, Walter Daelemans, and Tim C. E. Engels, “Journal Article Classification Using Abstracts: A Comparison of Classical and Transformer-based Machine Learning Methods,” Scientometrics 130, no. 1 (2024): 313–42, https://doi.org/10.1007/s11192-024-05217-7.
D. Arora, A. Bansal, N. Kumar, and A. Suri, “Invigorating Libraries with Application of Artificial Intelligence,” Library Philosophy and Practice, no. 3630 (2020), https://digitalcommons.unl.edu/libphilprac/3630.
Ferreira, “O Impacto da Inteligência Artificial na Gestão do Conhecimento em Bibliotecas Universitárias.”
FranciscoFoz, “Classificador de Assuntos e ODS (generative-ia),” Zenodo, June 12, 2024, https://doi.org/10.5281/zenodo.11592704.
Giuliano Ferreira, “O Impacto da Inteligência Artificial na Gestão do Conhecimento em Bibliotecas Universitárias: Desafios e Soluções,” in Anais do 22. Seminário Nacional de Bibliotecas Universitárias, 1–19 (SNBU, 2023), https://portal.febab.org.br/snbu2023/article/view/2934/2832.
H. Yin et al., “Leveraging Artificial Intelligence Technology for Mapping Research to Sustainable Development Goals: A Case Study,” arXiv, November 9, 2023, https://arxiv.org/abs/2311.16162.
J. Liu, J. Liu, and Y. Chen, “Application of Artificial Intelligence Technology in Information Retrieval of University Library,” in Innovative Computing, edited by J. C. Hung, J. W. Chang, Y. Pei, and W. C. Wu (Singapore: Springer, 2022), 221–28, https://doi.org/10.1007/978-981-16-4258-6_28.
Kyle Morgan, “Using AI to Auto-Tag Graduate Theses,” Information Technology and Libraries 44, no. 4 (2025), https://doi.org/10.5860/ital.v44i4.17381.
López-Regalado, Nuñez-Roja, Lopez-Gil, and Sanchez-Rodriguez, “Análisis del Uso de la Inteligencia Artificial.”
M. H. L. F. da S. Barros et al., “AI and Data Visualization for Enhanced Policy-Making: Aligning Research Initiatives with Sustainable Development Goals.” Sustainability 16, no. 24 (2024): 11050, https://doi.org/10.3390/su162411050.
Maycon Soave, and Daniela Lucas da Silva Lemos, “Curadoria Digital em Acervos do Patrimônio Cultural Digital: Aspectos Teóricos e Práticos no Âmbito da Ciência da Informação,” Brazilian Journal of Information Science: Research Trends 16 (2022): e02152, https://doi.org/10.36311/1981-1640.2022.v16.e02152.
Merih Angin et al., “A RoBERTa Approach for Automated Processing of Sustainability Reports,” Sustainability 14, no. 23 (2022): 16139, https://doi.org/10.3390/su142316139.
Muhammad Asim, Muhammad Arif, Muhammad Rafiq, and Rafiq Ahmad, “Investigating Applications of Artificial Intelligence in University Libraries of Pakistan: An Empirical Study,” The Journal of Academic Librarianship 49, no. 6 (2023): 102803, https://doi.org/10.1016/j.acalib.2023.102803.
Óscar López-Regalado, Norka Nuñez-Roja, Óscar R. Lopez-Gil, and José Sanchez-Rodriguez, “Análisis del Uso de la Inteligencia Artificial en la Educación Universitaria: Una Revisión Sistemática,” Pixel-Bit. Revista de Medios y Educación 70 (2024): 97–122, https://doi.org/10.12795/pixelbit.106336.
Rosario Gil García, “La Inteligencia Artificial en las Bibliotecas Universitarias Españolas,” Boletín de la Asociación Andaluza de Bibliotecarios 35, no. 138 (2024): 200–12, https://aab.es/wp-content/uploads/2024/12/128-BAAB-200-212.pdf.
S. Hervieux and A. Wheatley, “Perceptions of Artificial Intelligence: A Survey of Academic Librarians in Canada and the United States,” The Journal of Academic Librarianship 47, no. 1 (2021): 102270, https://doi.org/10.1016/j.acalib.2020.102270.
S. Olusegun Oyetola et al. “Artificial Intelligence in the Library: Gauging the Potential Application and Implications for Contemporary Library Services in Nigeria,” Data and Metadata 2 (2023): 36, https://doi.org/10.56294/dm202336.
Sarah Rúbia de Oliveira Santos and Célia da Consolação Dias, “Desafios para a Organização do Conhecimento no Âmbito das Humanidades Digitais e do Patrimônio Cultural: Um Olhar a Partir da Área de Informação e Ciência da Computação na Dimensions,” Encontros Bibli: Revista Eletrônica de Biblioteconomia e Ciência da Informação 29 (2024): 1–21, https://doi.org/10.5007/1518-2924.2024.e98058.
T. I. Yusuf, O. A. Adebayo, L. A. Bello, and J. O. Kayode, “Adoption of Artificial Intelligence for Effective Library Service Delivery in Academic Libraries in Nigeria,” Library Philosophy and Practice, no. 6804 (2022), https://digitalcommons.unl.edu/libphilprac/6804.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Francisco Tadeu Gonçalves de Oliveira Foz, Márcio Souza Martins, Oscar Eliel, Alessandra Karyne Clemente de Souza, Erica Cristina de Carvalho Mansur
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Authors that submit to Information Technology and Libraries agree to the Copyright Notice.
