Knowledge Graph Embedding in E-Government

Friday Orji; Okoni Bennett

doi:10.56201/ijcsmt.v11.no2.2025.pg97.105

📄 Download Paper

Knowledge Graph Embedding in E-Government

Friday Orji, Okoni Bennett

Abstract

The increasing adoption of Knowledge Graphs (KGs) in e-Government presents new opportunities for improving knowledge representation, inference, and decision-making in digital governance. However, real-world knowledge graphs often suffer from incompleteness, limiting their effectiveness in tasks such as policy analysis, citizen engagement, and service integration. To address this challenge, we explore Knowledge Graph Embedding (KGE), a Machine Learning (ML) technique, to generate meaningful vector representations of entities and relationships within an RDF/OWL knowledge graph developed using Protégé. Specifically, we apply TransE, a simple yet effective translational embedding model, to encode structured e-Government data and predict missing links. Our approach involves preprocessing the knowledge graph using RDFLib, extracting entity-relation triples, and leveraging PyKEEN for embedding computation and evaluation. The dataset is divided into 80% training, 10% validation, and 10% test sets, and model performance is assessed using standard metrics, including Mean Rank (MR), Mean Reciprocal Rank (MRR), and Hits@k (k = {1, 3, 10}). Experimental results reveal structural patterns within the e-Government knowledge graph, highlighting key entity clusters, relationship distributions, and link prediction trends. Furthermore, our analysis indicates that tail entity prediction tends to be more reliable than head entity prediction, suggesting areas for further optimization. Although TransE demonstrates promising results, challenges such as high variance in ranking metrics, dataset sparsity, and potential biases in entity distribution remain. Future research directions include hyperparameter tuning, integration of external ontologies, and the incorporation of neuro- symbolic AI techniques to enhance semantic reasoning. This study contributes to the advancement of knowledge representation in e-Government, showcasing the potential of KGE to s

Keywords

Knowledge GraphMachine LearningKnowledge Graph Embeddinge-GovernmentArtificial Intelligence

References

F. Orji, N. Nwiabu, B. Okoni, and O. Taylor, “A Knowledge Graph Model for e- Government,” Int. J. Innov. Sci. Res. Technol., vol. 9, no. 4, Apr. 2024. F. Orji, N. Nwiabu, O. Bennett, and O. Taylor, “A Knowledge Graph Data Transformation Model for e-Government,” E-Gov., vol. 2, no. 3, p. 4, 2024. F. Orji, N. Nwiabu, O. Bennett, and O. Taylor, “Artificial Intelligence in e-Government: A Computational Perspective Review”. F. Orji, N. Nwiabu, B. Okoni, and O. Taylor, “A Knowledge Graph Service Composition Model for e-Government,” Int. Res. J. Comput. Sci., vol. 11, no. 4, pp. 145–152, 2024. A. Bordes, N. Usunier, A. Garcia-Duran, J. Weston, and O. Yakhnenko, “Translating embeddings for modeling multi-relational data,” Adv. Neural Inf. Process. Syst., vol. 26, Z. Wang, J. Zhang, J. Feng, and Z. Chen, “Knowledge graph embedding by translating on hyperplanes,” in Proceedings of the AAAI conference on artificial intelligence, 2014. Y. Lin, Z. Liu, M. Sun, Y. Liu, and X. Zhu, “Learning entity and relation embeddings for knowledge graph completion,” in Proceedings of the AAAI conference on artificial intelligence, 2015. P. Hitzler, A. Eberhart, M. Ebrahimi, M. K. Sarker, and L. Zhou, “Neuro-symbolic approaches in artificial intelligence,” Natl. Sci. Rev., vol. 9, no. 6, p. nwac035, Jun. 2022, doi: 10.1093/nsr/nwac035. B. Perozzi, R. Al-Rfou, and S. Skiena, “Deepwalk: Online learning of social representations,” in Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining, 2014, pp. 701–710. A. Grover and J. Leskovec, “node2vec: Scalable feature learning for networks,” in Proceedings of the 22nd ACM SIGKDD international conference on Knowledge discovery and data mining, 2016, pp. 855–864. J. Tang, M. Qu, M. Wang, M. Zhang, J. Yan, and Q. Mei, “Line: Large-scale information network embedding,” in Proceedings of the 24th international conference on world wide web, 2015, pp. 1067–1077. T. N. Kipf and M. Welling, “Semi-supervised classification with graph convolutional networks,” ArXiv Prepr. ArXiv160902907, 2016. W. Hamilton, Z. Ying, and J. Leskovec, “Inductive representation learning on large graphs,” Adv. Neural Inf. Process. Syst., vol. 30, 2017. P. Velickovic et al., “Graph attention networks,” stat, vol. 1050, no. 20, pp. 10–48550, 2017. D. Wang, P. Cui, and W. Zhu, “Structural deep network embedding,” in Proceedings of the 22nd ACM SIGKDD international conference on Knowledge discovery and data mining, 2016, pp. 1225–1234.

Knowledge Graph Embedding in E-Government

Abstract

Keywords

References

More Articles from INTERNATIONAL JOURNAL OF COMPUTER SCIENCE AND MATHEMATICAL THEORY