TaCertoIssoAI: A Data Lake for Misinformation Analytics from WhatsApp in Brazil

• Cauê Paiva Lira Universidade de São Paulo (USP)
• Luiz Felipe Diniz Costa Universidade de São Paulo (USP)
• Pedro Henrique Ferreira Silva Universidade de São Paulo (USP)

DOI: https://doi.org/10.5753/sbbd_estendido.2026.249552

Resumo

This paper presents the analytics data lake of TaCertoIssoAI, a WhatsApp-based fact-checking platform operating in Brazil. Verified messages are anonymized and stored in a hybrid data architecture on Google Cloud, combining BigQuery for analytical workloads (OLAP) and Firestore for operational access (OLTP). The stored fact-checks follow a claim-oriented data model that supports multimodal content representations, together with vector embeddings for semantic search. A public analytics front-end allows users to filter, explore, and export fact-checking data. With over 7,200 users and 14,000 verified messages stored, the system provides a live dataset for analyzing misinformation patterns on messaging platforms and social media. The project has also won national technology competitions, been presented at a conference held at MIT, and received coverage from national news outlets such as G1.

Palavras-chave: semantic search, vector search, data lake, OLAP, OLTP, analytics, fact-checking, misinformation, WhatsApp, cloud, GCP

Referências

Akhtar, M., Schlichtkrull, M., Guo, Z., Cocarascu, O., Simperl, E., and Vlachos, A. (2023). Multimodal automated fact-checking: A survey. In Findings of the Association for Computational Linguistics: EMNLP 2023.

Gomes, J., Garcia, E., and Galvão Filho, A. R. (2025). Portuguese automated fact-checking: Information retrieval with claim extraction. In Proceedings of the FEVER Workshop.

Governo Digital, Brasil (2024). Guia sobre privacidade desde a concepção e por padrão. [link]. Accessed: 5 May 2026.

Guo, Z., Schlichtkrull, M., and Vlachos, A. (2022). A survey on automated fact-checking. Transactions of the Association for Computational Linguistics, 10:178–206. DOI: 10.1162/tacl_a_00454.

Hale, S. A., Humprecht, E., Esau, K., and Ferrara, E. (2024). Analyzing misinformation claims during the 2022 Brazilian general election on WhatsApp, Twitter, and Kwai. International Journal of Public Opinion Research.

IPTC (2024). IPTC media topics. [link]. Accessed: 5 May 2026.

Kuzman, T. and Ljubešić, N. (2025). LLM teacher-student framework for text classification with no manually annotated data: A case study in IPTC news topic classification. IEEE Access, 13:38772–38786. DOI: 10.1109/ACCESS.2025.3544814.

Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W.-t., Rocktäschel, T., Riedel, S., and Kiela, D. (2020). Retrieval-augmented generation for knowledge-intensive NLP tasks. In Advances in Neural Information Processing Systems (NeurIPS), volume 33, pages 9459–9474.

Sawadogo, P. and Darmont, J. (2021). On data lake architectures and metadata management. Journal of Intelligent Information Systems, 56(1):97–120. DOI: 10.1007/s10844-020-00608-7.

Song, H., Zhou, W., Cui, H., Peng, X., and Li, F. (2024). A survey on hybrid transactional and analytical processing. The VLDB Journal, 33:1485–1515. DOI: 10.1007/s00778-024-00858-9.

TaCertoIssoAI (2025a). TaCertoIssoAI – AI-powered fact-checking platform for WhatsApp. [link]. Accessed: 5 May 2026.

TaCertoIssoAI (2025b). TaCertoIssoAI analytics – microservice and web application. [link]. Accessed: 5 May 2026.

TaCertoIssoAI (2025c). TaCertoIssoAI deep fake detector. [link]. Accessed: 5 May 2026.

TaCertoIssoAI (2026). TaCertoIssoAI – analytics platform. [link]. Accessed: 6 May 2026.

Zhang, C., Li, G., Zhang, J., Zhang, X., and Feng, J. (2024). HTAP databases: A survey. IEEE Transactions on Knowledge and Data Engineering, 36:6410–6429. DOI: 10.1109/TKDE.2024.3389693.