Exploring the Use of Large Language Model (ChatGPT) for Semantic Alignment betweenGeospatial Data Conceptual Schemas
Article Sidebar
Main Article Content
Abstract
Given the current scenario, where the exponential growth in the production of geospatial data converges with the need for its dissemination and sharing, the development of mechanisms that facilitate data interoperability, whose sources of production may be diverse, becomes crucial. Thus, issues aimed at promoting semantic interoperability processes between different conceptual models of these data become relevant. Accordingly, this paper investigates the potential use of a natural language processing tool, built on a Large Language Model (LLM), as a facilitator for the future automation of semantic alignment mechanisms between different conceptual schemas. As a result, the tool used – ChatGPT – presented 123 semantic associations between the utilized schemas: 34 classes from the building category of Brazil's reference cartographic base and various tags applied for creating voluntary data in OpenStreetMap (OSM). In some cases, the associations were detailed, while in others, they were more general, allowing for comparison with previous work manually conducted by humans. It is important to highlight the significant role of constructing the alignment request dialogue, with structured organization of conceptual data, as well as the use of clear and unambiguous dialogue. There are still limitations in the process, particularly in understanding the hierarchy of the concepts used, indicating the need for further studies and evaluation of other available LLMs. Nevertheless, the use of artificial intelligence for the semantic interoperability of geospatial data emerges as a viable path to be applied.
Downloads
Article Details
Section
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish in this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors can enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) before and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (see "The Effect of Open Access").
How to Cite
References
Anand, S., Morley, J., Jiang, W., Du, H., & Hart, G. (2010). When worlds collide: Combining Ordnance Survey and Open Street Map data. AGI Geocommunity '10, London, UK.
Ballatore, A., Bertolotto, M., & Wilson, D. C. (2013). Geographic knowledge extraction and semantic similarity in OpenStreetMap. Knowledge and Information Systems, 37(1), 61–81. https://doi.org/10.1007/s10115-012-0571-0.
Borges, K. A. V.; Davis Jr., C. A. & Laender, A. H. F. (2005). Modelagem conceitual de dados geográficos. In: Casanova, M. A.; Câmara, G.; Davis Jr., C. A.; Vinhas, L. & Queiroz, G. R. de (ed). Bancos de Dados Geográficos. Curitiba, Editora MundoGEO. http://www.dpi.inpe.br/livros/bdados/
Bortolini, E., Silva, L. S. L., Machado, A. A., Paiva, C. D. A., & Camboim, S. P. (2018). Potenciais categorias de informações geográficas do mapeamento colaborativo para o mapeamento oficial. Colóquio Brasileiro de Ciências Geodésicas, X. Curitiba-PR.
Bortolini, E.; Silva, L. S. L.; Elias, E. N. N.; Camboim, S. P. & Schmidt, M. A. R. (2020). Sinergias entre a produção dos dados geoespaciais de referência oficiais e colaborativos: uma proposição de eixos potenciais. Simpósio Brasileiro de Infraestrutura de Dados Espaciais, II. Rio de Janeiro-RJ.
Brasil. (2010). Plano de Ação para Implantação da Infraestrutura Nacional de Dados Espaciais – INDE. 1° ed. Ministério do Planejamento, Orçamento e Gestão, Comissão Nacional de Cartografia. Brasília-DF.
Bravo, J. V. M. (2014). A confiabilidade semântica das informações geográficas voluntárias como função da organização mental do conhecimento espacial. Dissertação de Mestrado. 139 p. Universidade Federal do Paraná, Programa de Pós-Graduação em Ciências Geodésicas, Curitiba-PR.
Brovelli, M. A., Minghini, M., Molinari, M. E., & Zamboni, G. (2016). Positional accuracy assessment of the openstreetmap buildings layer through automatic homologous pairs detection: the method and a case study. ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLI-B2, 615–620. https://doi.org/10.5194/isprsarchives-XLI-B2-615-2016.
Concar. (2017). Comissão Nacional de Cartografia. Especificações Técnicas para Estruturação de Dados Geoespaciais Vetoriais (ET-EDGV 3.0). NCB-CC/E 0001B08. Versão 3.0.
Dang, H., Mecke, L., Lehmann, F., Goller, S., & Buschek, D. (2022). How to Prompt? Opportunities and Challenges of Zero- and Few-Shot Learning for Human-AI Interaction in Creative Applications of Generative Models (arXiv:2209.01390). arXiv. http://arxiv.org/abs/2209.01390.
Elias, E. N. N., & Fernandes, V. de O. (2019). Quality Analysis of OpenStreetMap Geospatial Data for Positional Accuracy, Thematic Accuracy and Completeness indicators. pp., 30(2).
Fernandes, V. O., Elias, E. N., & Zipf, A. (2020). Integration of authoritative and volunteered geographic information for updating urban mapping: challenges and potentials. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLIII-B4-2020, 261–268. https://doi.org/10.5194/isprs-archives-XLIII-B4-2020-261-2020.
Grinberger, A. Y., Minghini, M., Juhász, L., Yeboah, G., & Mooney, P. (2022). OSM Science - The Academic Study of the OpenStreetMap Project, Data, Contributors, Community, and Applications. ISPRS International Journal of Geo-Information, 11(4), 230. https://doi.org/10.3390/ijgi11040230.
ISO. (2015). ISO 19103:2015. Geographic information - Conceptual schema language. International Organization for Standardization (ISO).
Jozefowicz, R., Vinyals, O., Schuster, M., Shazeer, N., & Wu, Y. (2016). Exploring the Limits of Language Modeling (arXiv:1602.02410). arXiv. http://arxiv.org/abs/1602.02410.
Kaur, J., Singh, J., Sehra, S. S., & Rai, H. S. (2017). Systematic Literature Review of Data Quality Within OpenStreetMap. International Conference on Next Generation Computing and Information Systems (ICNGCIS), 177–182. https://doi.org/10.1109/ICNGCIS.2017.35.
Kuhn, W. (2003). Semantic reference systems. International Journal of Geographical Information Science, 17(5), 405–409. https://doi.org/10.1080/1365881031000114116.
Longley, P. A.; Goodchild, M. F.; Maguire, D. J.; Rhind, D. W. (2011). Geographic Information Systems and Science. 3rd ed. Hoboken: Wiley.
Machado, A. A., & Camboim, S. P. (2019). Mapeamento colaborativo como fonte de dados para o planejamento urbano: Desafios e potencialidades. urbe. Revista Brasileira de Gestão Urbana, 11, e20180142. https://doi.org/10.1590/2175-3369.011.e20180142.
Machado, A. A. (2020). Compatibilização Semântica entre o Modelo de Dados do OpenStreetMap e a Especificação Técnica para Estruturação de Dados Geoespaciais Vetoriais (ET-EDGV). Tese de douto-rado em ciências geodésicas. Setor de Ciências da Terra, Universidade Federal do Paraná. Curitiba-PR.
Machado, A. A., & Camboim, S. P. (2024). Semantic Alignment of Official and Collaborative Geospatial Data: A Case Study in Brazil. Revista Brasileira de Cartografia, 76. Scopus. https://doi.org/10.14393/rbcv76n0a-72070.
McCarthy, J.; Minsky, M. L.; Rochester, N.; Shannon, C. E. (1955). A Proposal for the Dartmouth Summer Research Project on Artificial Intelligence. AI Magazine. 27(4).
Ministério da Defesa. (2018). Norma da Especificação Técnica para Aquisição de Dados Geoespaciais Vetoriais (EB80-N-72.005). ET-ADGV. 1ª Edição. Exército Brasileiro; Departamento de Ciência e Tecnologia; Diretoria de Serviço Geográfico.
Mooney, P., Cui, W., Guan, B., & Juhász, L. (2023). Towards Understanding the Geospatial Skills of ChatGPT: Taking a Geographic Information Systems (GIS) Exam. https://doi.org/10.31223/X5P38P.
OGC. Open Geospatial Consortium. (2023). Standards. https://www.ogc.org/standards/.
OGC. Open Geospatial Consortium. (2020). Benefits of Representing Spatial Data Using Semantic and Graph Technologies. http://www.opengis.net/doc/wp/using-semantic-graph.
OSM. (2024). Map Features. https://wiki.OpenStreetMap.org/wiki/Map_features.
Petchenik, B. B. (1977). Cognition In Cartography. Cartographica: The International Journal for Geographic Information and Geovisualization, 14(1), 117–128. https://doi.org/10.3138/97R4-84N4-4226-0P24.
Prince, S. J. D. (2023). Understanding Deep Learning. http://udlbook.com.
Robinson, A. C., Demšar, U., Moore, A. B., Buckley, A., Jiang, B., Field, K., Kraak, M.-J., Camboim, S. P., & Sluter, C. R. (2017). Geospatial big data and cartography: Research challenges and opportunities for making maps that matter. International Journal of Cartography, 3(sup1), 32–60. https://doi.org/10.1080/23729333.2016.1278151.
Rosch, E. (1975). Cognitive Representations of Semantic Categories. Journal of Experimental psychology: General. 104(3).
Santhanam, S., & Shaikh, S. (2019). A Survey of Natural Language Generation Techniques with a Focus on Dialogue Systems - Past, Present and Future Directions (arXiv:1906.00500). arXiv. http://arxiv.org/abs/1906.00500.
Segaran, T. (2007). Programming Collective Intelligence: Building Smart Web 2.0 Applications. 1ª edição. Ed O’Reilly.
Silva, A. E. de S.; Camboim, S. P.; Delazari, L. S. (2022). O Problema da Compatibilidade Semântica entre as Representações Cartográficas do OpenStreetMap, ET-EDGV e OHI. XII Colóquio Brasileiro de Ciências Geodésicas – CBCG e V Simpósio Brasileiro de Geomática – SBG.
Silva, L. S. da; Teixeira, R. R. P. (2022). Filosofia da mente e inteligência artificial em atividades de divulgação científica mediadas por recursos audiovisuais. Revista Mundi Sociais e Humanidades. Paranaguá, PR, 07(01), 01-27.
Silva, L. S. L. (2022). Integração de Dados Provenientes de Mapeamento Colaborativo na Cartografia de Referência do Brasil. Tese de doutorado em Ciências Geodésicas da Universidade Federal do Paraná.
Silva, L. S. L., & Camboim, S. P. (2020). Brazilian NSDI ten years later: current overview, new challenges and propositions for national topographic mapping. Boletim de Ciências Geodésicas, 26(4), e2020018. https://doi.org/10.1590/s1982-21702020000400018.
Sluter, C. R., Camboim, S. P., Iescheck, A. L., & Pereira, L. B. Castro, M. C.; Yamada, M. M.; Araújo, V. S. (2019). A proposal of topographic map symbols for large-scale maps of urban areas in Brazil. Abstracts of the ICA, 1, 362-377. https://doi.org/10.1080/00087041.2018.1549307.
Souza, F. A., & Camboim, S. P. (2023). Semantic Alignment of Geospatial Data Models using ChatGPT: preliminary studies. Fonseca F. F. da & Vinhas L. (Orgs.), Proc. Brazilian Symp. GeoInformatics (p. 399–404). National Institute for Space Research, INPE; Scopus. https://www.scopus.com/inward/record.uri?eid=2-s2.0-85181118913&partnerID=40&md5=45de9b24f4242bc1e4306f46b84a1ed0.
Vasconcellos, S. J. L., & Machado, S. D. S. (2006). Construtivismo, psicologia experimental e neurociência. Psicologia Clínica, 18(1), 83–94. https://doi.org/10.1590/S0103-56652006000100007.
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., & Polosukhin, I. (2017). Attention is All you Need. 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA.
Wang, J., Liu, Z., Zhao, L., Wu, Z., Ma, C., Yu, S., Dai, H., Yang, Q., Liu, Y., Zhang, S., Shi, E., Pan, Y., Zhang, T., Zhu, D., Li, X., Jiang, X., Ge, B., Yuan, Y., Shen, D., … Zhang, S. (2023). Review of Large Vision Models and Visual Prompt Engineering (arXiv:2307.00855). arXiv. http://arxiv.org/abs/2307.00855.
Yu, L., Qiu, P., Liu, X., Lu, F., & Wan, B. (2018). A holistic approach to aligning geospatial data with multidimensional similarity measuring. International Journal of Digital Earth, 11(8), 845–862. https://doi.org/10.1080/17538947.2017.1359688.
Zhang, Q., Zhang, T., Zhai, J., Fang, C., Yu, B., Sun, W., & Chen, Z. (2024). A Critical Review of Large Language Model on Software Engineering: An Example from ChatGPT and Automated Program Repair (arXiv:2310.08879). arXiv. http://arxiv.org/abs/2310.08879.