Knowledge Graph for Covid-19: a data fusion approach

• André Cerri UFRJ
• Diogo Nolasco UFRJ
• Jonice Oliveira UFRJ

DOI: https://doi.org/10.5753/sbcas_estendido.2026.26541

Resumo

The Covid-19 pandemic generated a rapid and heterogeneous growth of scientific, technological, and social data, making it difficult for researchers and decision-makers to follow the available evidence in a timely manner. To address this problem, this paper presents the Knowledge Graph for Covid-19 (KGC-19), a knowledge graph designed to integrate information from PubMed articles, WIPO, EPO and LATIPAT patents, and X (formerly Twitter) posts. The proposed pipeline uses ETL scripts to collect, filter, standardize, and load the data into Neo4j according to a previously defined ontology. Named Entity Recognition models, including Flair and BioNER, are then applied to identify additional entities in texts and enrich the graph. The resulting graph connects scientific, technological, and social entities, enabling semantic queries and multidimensional analysis in the Covid-19 domain. KGC-19 therefore offers a promising approach to organize large volumes of unstructured pandemic-related data and support the discovery of relationships between research production, technological development, and social perception.

Referências

Akbik, A., Bergmann, T., Blythe, D., Rasul, K., Schweter, S., and Vollgraf, R. (2019). Flair: An easy-touse framework for state-of-the-art nlp. In NAACL 2019, 2019 Annual Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations), pages 54–59.

Al-Obeidat, F., Adedugbe, O., Hani, A. B., Benkhelifa, E., and Majdalawieh, M. (2020). Cone-kg: A semantic knowledge graph with news content and social context for studying covid-19 news articles on social media. In Proceedings of the 2020 Seventh International Conference on Social Networks Analysis, Management and Security (SNAMS), pages 1–7. IEEE.

Castanedo, F. (2013). A review of data fusion techniques. The scientific world journal, 2013(1):704504.

Devlin, J., Chang, M.-W., Lee, K. w., and Toutanova, K. (2019). Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers), pages 4171–4186.

Guizzardi, G., de Almeida Falbo, R., and Guizzardi, R. S. (2008). Grounding software domain ontologies in the unified foundational ontology (ufo): The case of the ode software process ontology. In Proceedings of the XI Ibero-American Conference on Software Engineering (CIbSE), pages 127–140.

Khan, M. R., Ziyadi, M., and AbdelHady, M. (2020). Mt-bioner: Multi-task learning for biomedical named entity recognition using deep bidirectional transformers. arXiv preprint arXiv:2001.08904.

Lee, J., Yoon, W., Kim, S., Kim, D., Kim, S., So, C. H., and Kang, J. (2020). Biobert: a pre-trained biomedical language representation model for biomedical text mining. Bioinformatics, 36(4):1234–1240.

Li, L., Wang, P., Yan, J., Wang, Y., Li, S., Jiang, J., Sun, Z., Tang, B., Chang, T. H., Wang, S., and Liu, Y. (2020). Real-world data medical knowledge graph: construction and applications. Artificial Intelligence in Medicine, 103:101817.

Li, X., Zhang, K., Li, G., and Zhu, B. (2021). A chinese knowledge graph for cardiovascular disease. In Liang, Q., Wang, W., Liu, X., Na, Z., Li, X., and Zhang, B., editors, Communications, Signal Processing, and Systems, pages 1816–1826, Singapore. Springer Singapore.

Manica, M., Auer, C., Weber, V., Zipoli, F., Dolfi, M., Staar, P., Laino, T., Bekas, C., Fujita, A., Toda, H., Hirose, S., and Orii, Y. (2019). An information extraction and knowledge graph platform for accelerating biochemical discoveries. arXiv preprint arXiv:1907.05167.

Mohit, B. (2014). Named Entity Recognition, pages 221–245. Springer Berlin Heidelberg, Berlin, Heidelberg.

Qiao, L., Yang, L., Hong, D., Yao, L., and Zhiguang, Q. (2016). Knowledge graph construction techniques. Journal of computer research and development, 53(3):582–600.

Singh, S. (2018). Natural language processing for information extraction. arXiv preprint arXiv:1807.02383.

Wang, C., Ma, X., Chen, J., and Chen, J. (2018). Information extraction and knowledge graph construction from geoscience literature. Computers and Geosciences, 112:112–120.

Wang, L. L., Lo, K., Chandrasekhar, Y., Reas, R., Yang, J., Burdick, D., Eide, D., Funk, K., Katsis, Y., Kinney, R., Li, Y., Liu, Z., Merrill, W., Mooney, P., Murdick, D., Rishi, D., Sheehan, J., Shen, Z., Stilson, B., Wade, A., Wang, K., Wang, N. X. R., Wilhelm, C., Xie, B., Raymond, D., Weld, D. S., Etzioni, O., and Kohlmeier, S. (2020). Cord-19: The covid-19 open research dataset. arXiv preprint arXiv:2004.10706.

Wang, Q., Li, M., Wang, X., Parulian, N., Han, G., Ma, J., Tu, J., Lin, Y., Zhang, H., Liu, W., Chauhan, A., Guan, Y., Li, B., Li, R., Song, X., Fung, Y. R., Ji, H., Han, J., Chang, S.-F., Pustejovsky, J., Rah, J., Liem, D., Elsayed, A., Palmer, M., Voss, C., Schneider, C., and Onyshkevych, B. (2021). Covid-19 literature knowledge graph construction and drug repurposing report generation. arXiv preprint arXiv:2007.00576.

Wang, Q., Mao, Z., Wang, B., and Guo, L. (2017). Knowledge graph embedding: A survey of approaches and applications. IEEE Transactions on Knowledge and Data Engineering, 29(12):2724–2743.

Wise, C., Calvo, M. R. S., Bhatia, P., Ioannidis, V., Karypus, G., Price, G., Song, X., Brand, R., and Kulkani, N. (2020). Covid-19 knowledge graph: accelerating information retrieval and discovery for scientific literature. In Proceedings of knowledgeable NLP: the first workshop on integrating structured knowledge and neural networks for NLP, pages 1–10.

Xiong, C., Power, R., and Callan, J. (2017). Explicit semantic ranking for academic search via knowledge graph embedding. In Proceedings of the 26th international conference on world wide web, pages 1271–1279.

Zhang, R., Hristovski, D., Schutte, D., e Marcelo Fiszman, A. K., and Kilicoglu, H. (2021). Drug repurposing for covid-19 via knowledge graph completion. Journal of Biomedical Informatics, 115:103696.