SWInG: A SemanticWeb Integrated with Generative AI Architecture for Dynamic Data Generation
Resumo
Introduction: This paper proposes an architecture that combines Semantic Web technologies and Generative Artificial Intelligence to automate the creation and maintenance of content data in digital games and other applications across configurable contexts. The architecture uses semantic databases as the primary data source and leverages Generative AI to fill in missing information and suggest corrections. Objective: The goal is a semiautomated architecture that reduces content curation workload while keeping data current and relevant. The approach also seeks to optimize Generative AI use, thereby reducing the financial costs of content generation. Methodology: The architecture utilizes semantic databases and Generative AI, integrating an AI confidence score mechanism to support content curation across various domains. An online quiz game was developed using Wikidata and OpenAI APIs as a proof of concept. Results: By extracting 1,241 values out of an expected 1,576 from the Semantic Web, the study identified 335 missing values and demonstrated how AI-generated content, accompanied by confidence scores, can effectively supplement these gaps. The results show that most AI-generated values have high confidence (above 86%), with certain properties reaching nearly 100%.
Palavras-chave:
Content Generation, Semantic Web, Generative Artificial Intelligence, Serious games
Referências
Arnab, S., Lim, T., Carvalho, M. B., Bellotti, F., de Freitas, S., Louchart, S., Suttie, N., Berta, R., e De Gloria, A. (2015). Mapping learning and game mechanics for serious games analysis. British Journal of Educational Technology, 46(2):391–411. _eprint: [link].
Bellotti, F., Kapralos, B., Lee, K., Moreno-Ger, P., e Berta, R. (2013). Assessment in and of Serious Games: An Overview. Advances in Human-Computer Interaction, 2013(1):136864.
Berners-Lee, T., Hendler, J., e Lassila, O. (2001a). The Semantic Web. Scientific American, 284(5):34–43.
Berners-Lee, T., Hendler, J., e Lassila, O. (2001b). The semantic web: A new form of web content that is meaningful to computers will unleash a revolution of new possibilities. ScientificAmerican.com.
Clark, P., Tafjord, O., e Richardson, K. (2020). Transformers as Soft Reasoners over Language. arXiv:2002.05867 [cs].
Elfotouh, A. M. A., Nasr, E. S., e Gheith, M. H. (2017). Towards a comprehensive serious educational games’ ontology. In Proceedings of the 3rd Africa and Middle East Conference on Software Engineering, AMECSE ’17, page 25–30, New York, NY, USA. Association for Computing Machinery.
Goodfellow, I., Bengio, Y., e Courville, A. (2016). Deep Learning. MIT Press.
Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., e Bengio, Y. (2014). Generative Adversarial Nets. In Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N., e Weinberger, K. Q., editors, Advances in Neural Information Processing Systems, volume 27. Curran Associates, Inc.
Hat, R. (2023). What is generative AI? [link]. Accessed: Apr. 04, 2024.
Horrocks, I., Parsia, B., Patel-Schneider, P., e Hendler, J. (2005). Semantic web architecture: Stack or two towers? In Fages, F. e Soliman, S., editors, Principles and Practice of Semantic Web Reasoning, pages 37–41, Berlin, Heidelberg. Springer Berlin Heidelberg.
Lassila, O., Swick, R. R., et al. (1998). Resource description framework (rdf) model and syntax specification.
Mao, X., Yu, W., Yamada, K. D., e Zielewski, M. R. (2024). Procedural Content Generation via Generative Artificial Intelligence. _eprint: 2407.09013.
Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C. L., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., Schulman, J., Hilton, J., Kelton, F., Miller, L., Simens, M., Askell, A., Welinder, P., Christiano, P., Leike, J., e Lowe, R. (2022). Training language models to follow instructions with human feedback. _eprint: 2203.02155.
Rashid, M., Torchiano, M., Rizzo, G., Mihindukulasooriya, N., e Corcho, Ó. (2019). A quality assessment approach for evolving knowledge bases. Semantic Web, 10(2):349– 383.
Shadbolt, N., Berners-Lee, T., e Hall, W. (2006). The Semantic Web Revisited. IEEE Intelligent Systems, 21(3):96–101.
Summerville, A., Snodgrass, S., Guzdial, M., Holmgård, C., Hoover, A. K., Isaksen, A., Nealen, A., e Togelius, J. (2018). Procedural Content Generation via Machine Learning (PCGML). _eprint: 1702.00539.
van Ossenbruggen, J., Hardman, L., e Rutledge, L. (2001). Hypermedia and the semantic web: A research agenda. Journal of Digital information, 3(1).
Vrandečić, D. e Krötzsch, M. (2014). Wikidata: a free collaborative knowledgebase. Communications of the ACM, 57(10):78–85.
Bellotti, F., Kapralos, B., Lee, K., Moreno-Ger, P., e Berta, R. (2013). Assessment in and of Serious Games: An Overview. Advances in Human-Computer Interaction, 2013(1):136864.
Berners-Lee, T., Hendler, J., e Lassila, O. (2001a). The Semantic Web. Scientific American, 284(5):34–43.
Berners-Lee, T., Hendler, J., e Lassila, O. (2001b). The semantic web: A new form of web content that is meaningful to computers will unleash a revolution of new possibilities. ScientificAmerican.com.
Clark, P., Tafjord, O., e Richardson, K. (2020). Transformers as Soft Reasoners over Language. arXiv:2002.05867 [cs].
Elfotouh, A. M. A., Nasr, E. S., e Gheith, M. H. (2017). Towards a comprehensive serious educational games’ ontology. In Proceedings of the 3rd Africa and Middle East Conference on Software Engineering, AMECSE ’17, page 25–30, New York, NY, USA. Association for Computing Machinery.
Goodfellow, I., Bengio, Y., e Courville, A. (2016). Deep Learning. MIT Press.
Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., e Bengio, Y. (2014). Generative Adversarial Nets. In Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N., e Weinberger, K. Q., editors, Advances in Neural Information Processing Systems, volume 27. Curran Associates, Inc.
Hat, R. (2023). What is generative AI? [link]. Accessed: Apr. 04, 2024.
Horrocks, I., Parsia, B., Patel-Schneider, P., e Hendler, J. (2005). Semantic web architecture: Stack or two towers? In Fages, F. e Soliman, S., editors, Principles and Practice of Semantic Web Reasoning, pages 37–41, Berlin, Heidelberg. Springer Berlin Heidelberg.
Lassila, O., Swick, R. R., et al. (1998). Resource description framework (rdf) model and syntax specification.
Mao, X., Yu, W., Yamada, K. D., e Zielewski, M. R. (2024). Procedural Content Generation via Generative Artificial Intelligence. _eprint: 2407.09013.
Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C. L., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., Schulman, J., Hilton, J., Kelton, F., Miller, L., Simens, M., Askell, A., Welinder, P., Christiano, P., Leike, J., e Lowe, R. (2022). Training language models to follow instructions with human feedback. _eprint: 2203.02155.
Rashid, M., Torchiano, M., Rizzo, G., Mihindukulasooriya, N., e Corcho, Ó. (2019). A quality assessment approach for evolving knowledge bases. Semantic Web, 10(2):349– 383.
Shadbolt, N., Berners-Lee, T., e Hall, W. (2006). The Semantic Web Revisited. IEEE Intelligent Systems, 21(3):96–101.
Summerville, A., Snodgrass, S., Guzdial, M., Holmgård, C., Hoover, A. K., Isaksen, A., Nealen, A., e Togelius, J. (2018). Procedural Content Generation via Machine Learning (PCGML). _eprint: 1702.00539.
van Ossenbruggen, J., Hardman, L., e Rutledge, L. (2001). Hypermedia and the semantic web: A research agenda. Journal of Digital information, 3(1).
Vrandečić, D. e Krötzsch, M. (2014). Wikidata: a free collaborative knowledgebase. Communications of the ACM, 57(10):78–85.
Publicado
30/09/2025
Como Citar
FREITAS, Wagner Luis Cardozo Gomes de; SILVA JUNIOR, Jose Ricardo da.
SWInG: A SemanticWeb Integrated with Generative AI Architecture for Dynamic Data Generation. In: SIMPÓSIO BRASILEIRO DE JOGOS E ENTRETENIMENTO DIGITAL (SBGAMES), 24. , 2025, Salvador/BA.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 563-574.
DOI: https://doi.org/10.5753/sbgames.2025.10018.
