Automated Collective Digital Memorial: an AI-powered workflow for data curation

• Luís Flávio Ferreira Monteiro Federal University of Mato Grosso http://orcid.org/0000-0003-1865-7046
• Cristiano Maciel Federal University of Mato Grosso https://orcid.org/0000-0002-2431-8457

DOI: https://doi.org/10.5753/ihc_estendido.2025.13247

Abstract

Introduction: Generating collective digital memorials from public web data requires workflows that balance speed; privacy and cultural sensitivity. Objective: To propose a four-step workflow for creating collective digital memorials using publicly available web data. Steps: Scrape sources; clean extracted content; classify items with the local Gemma 3-1B model and produce automatic summaries. Results: In tests with two real profiles; assembly time fell from about 25 minutes to 1.6 minutes (93% reduction) and section-based organization reached around 85% accuracy. The system runs locally; preserves privacy and requires brief human review to ensure cultural sensitivity. Limitations include a restricted test set and dependence on a compact model. Future work will explore larger models; multimodal support and evaluations with grieving families.

Keywords: Digital Legacy, Death, Artificial Intelligence, Digital Memorial, Collective, Data Curation

References

Beppu, F., Maciel, C., & Viterbo, J. (2021). Contributions of the Brazilian Act for the Protection of Personal Data for treating Digital Legacy. Journal on Interactive Systems, 12, 112-124. DOI: 10.5753/jis.2021.1654. Acesso em: 20 ago. 2025.

Bird, S., Klein, E., & Loper, E. (2009). Natural language processing with Python: analyzing text with the natural language toolkit. O'Reilly Media, Inc.

Brown, M. A., Gruen, A., Maldoff, G., Messing, S., Sanderson, Z., & Zimmer, M. (2024). Web Scraping for Research: Legal, Ethical, Institutional, and Scientific

Considerations. arXiv preprint arXiv:2410.23432. Disponível em: [link]. Acesso em: 20 ago. 2025.

Creswell, J. W., Creswell, J. D. (2018). Research Design: Qualitative, Quantitative, and Mixed Methods Approaches. SAGE Publications, Los Angeles, CA, 5th edition.

Dados Além da Vida (DAVI). (2025). DAVI | Dados Além da Vida. Disponível em: [link]. Acesso em: 20 ago. 2025.

Gemma Team. (2025). Gemma 3 Technical Report. arXiv preprint arXiv:2503.19786. Disponível em: [link]. Acesso em: 20 ago. 2025.

Gil, A. C. (2019). Como elaborar projetos de pesquisa. 6. ed. São Paulo: Atlas.

Lopes, A. D., Maciel, M., & Pereira, V. C. (2014). Recomendações para o design de memórias digitais na web social. In Proceedings of the 13th Brazilian Symposium on Human Factors in Computing Systems (IHC '14). Sociedade Brasileira de Computação, 275–284.

McKinney, W. (2010). Data structures for statistical computing in Python. In Proceedings of the 9th Python in Science Conference (pp. 51-56).

Ni, J., Li, J., & McAuley, J. (2021). Sentence-T5: Scalable sentence encoders from pre-trained text-to-text models. arXiv preprint arXiv:2108.08877. Disponível em: [link]. Acesso em: 20 ago. 2025.

Öhman, C. J., & Watson, D. (2019). Are the dead taking over Facebook? A Big Data approach to the future of death online. Big Data & Society, 6(1), 2053951719842540. DOI: 10.1177/2053951719842540. Acesso em: 20 ago. 2025.

Pereira, R.; et al. (2024). GranDIHC-BR: Grand Research Challenges in Human-Computer Interaction in Brazil for 2025–2035. IHC 2024 – Anais Estendidos. Disponível em: [link]. Acesso em: 20 ago. 2025.

Reitz, K. (2025). Requests: HTTP for Humans. Disponível em: [link]. Acesso em: 20 ago. 2025.

Richardson, L. (2025). Beautiful Soup. Disponível em: [link]. Acesso em: 20 ago. 2025.

Selenium Developers. (2025). Selenium WebDriver. Disponível em: [link]. Acesso em: 20 ago. 2025.

Sommerville, I. (2015). Software Engineering. 10th Edition, Pearson Education Limited, Boston.

Trevisan, D., Maciel, C., & Bim, S. A. (2021). Educação, morte e tecnologias - experiência no ensino de avaliação em IHC. In Anais Estendidos do XX Simpósio Brasileiro de Fatores Humanos em Sistemas Computacionais (IHC), 56-63. Porto Alegre: SBC. Disponível em: [link]. Acesso em: 20 ago. 2025.

Ueda, G., Monteiro, L. F. F., Maciel, C., & Pereira, V. C. (2022). Digital memorials: classifications and design recommendations. Journal on Interactive Systems, 13(1), 335–349. Disponível em: [link]. Acesso em: 20 ago. 2025.

Wolf, T., et al. (2019). HuggingFace’s Transformers: State-of-the-art Natural Language Processing. arXiv 1910.03771. Disponível em: [link]. Acesso em: 20 ago. 2025.