LLM-Based Summarization of Academic Communities Using Relational Group Characterization
Resumo
A caracterização de comunidades é uma etapa fundamental na análise de redes sociais. Embora métodos tradicionais utilizem termos representativos para rotular comunidades, o entendimento dessas descrições pode ser limitado. Este trabalho investiga o uso de LLMs para sumarizar comunidades acadêmicas a partir de termos obtidos por métodos relacionais. Para isso, foram analisadas comunidades detectadas em uma rede de coautoria do repositório arXiv, considerando diferentes métodos de caracterização e medidas de centralidade. Os resultados indicam que distintas centralidades produzem representações semânticas diferentes e que os LLMs geram sumarizações consistentes e informativas mesmo a partir de poucos termos.Referências
Allan, S. (2025). Estatísticas das redes sociais em 2026: últimas tendências e dados. [link]. Acesso em: 23 maio 2026.
Fortunato, S. and Hric, D. (2016). Community detection in networks: A user guide. Physics Reports, 659:1–44.
Getoor, L. and Diehl, C. P. (2005). Link mining: a survey. SIGKDD Exploration Newsletter, 7(2):3–12.
Gomes, J. a. E. A., Prudêncio, R. B. C., and Nascimento, A. C. A. (2018). Centrality-based group profiling: A comparative study in co-authorship networks. New Gen. Comput., 36(1):59–89.
Gomes, J. E. A. (2018). Caracterização de Grupos Baseada em Informações Relacionais. Tese de doutorado, Universidade Federal de Pernambuco, Recife.
McPherson, M., Smith-Lovin, L., and Cook, J. M. (2001). Birds of a feather: Homophily in social networks. Annual Review of Sociology, 27:415–444.
Rahimzadeh, V., Hamzehpour, A., Shakery, A., and Asadpour, M. (2025). From millions of tweets to actionable insights: Leveraging llms for user profiling.
Reimers, N. and Gurevych, I. (2019). Sentence-bert: Sentence embeddings using siamese bert-networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics.
Savić, M., Ivanović, M., Radovanović, M., Ognjanović, Z., Pejović, A., and Jakšić Krüger, T. (2015). ICT Innovations 2014: World of Data, chapter Exploratory Analysis of Communities in Co-authorship Networks: A Case Study, pages 55–64. Springer International Publishing, Cham.
Tang, L. and Liu, H. (2010). Community Detection and Mining in Social Media. Morgan and Claypool, New York, USA.
Tang, L., Wang, X., and Liu, H. (2011). Group profiling for understanding social structures. ACM Trans. Intell. Syst. Technol., 3(1).
Wang, Q., Erqsous, M., Barner, K. E., and Mauriello, M. L. (2025). Lata: A pilot study on llm-assisted thematic analysis of online social network data generation experiences. Proc. ACM Hum.-Comput. Interact., 9(2).
Wasserman, S. and Faust, K. (1994). Social Network Analysis: methods and applications (structural analysis in the social sciences). Cambridge University Press, New York, USA.
Yin, M., Liu, H., Lian, B., and Cai, R. (2026). Copersona: Leveraging llms and expert collaboration to understand user personas through social media data analysis. Design for Augmented Humanity, 1(1):49–66.
Zhang, T., Kishore, V., Wu, F., Weinberger, K. Q., and Artzi, Y. (2020). Bertscore: Evaluating text generation with bert. In International Conference on Learning Representations.
Fortunato, S. and Hric, D. (2016). Community detection in networks: A user guide. Physics Reports, 659:1–44.
Getoor, L. and Diehl, C. P. (2005). Link mining: a survey. SIGKDD Exploration Newsletter, 7(2):3–12.
Gomes, J. a. E. A., Prudêncio, R. B. C., and Nascimento, A. C. A. (2018). Centrality-based group profiling: A comparative study in co-authorship networks. New Gen. Comput., 36(1):59–89.
Gomes, J. E. A. (2018). Caracterização de Grupos Baseada em Informações Relacionais. Tese de doutorado, Universidade Federal de Pernambuco, Recife.
McPherson, M., Smith-Lovin, L., and Cook, J. M. (2001). Birds of a feather: Homophily in social networks. Annual Review of Sociology, 27:415–444.
Rahimzadeh, V., Hamzehpour, A., Shakery, A., and Asadpour, M. (2025). From millions of tweets to actionable insights: Leveraging llms for user profiling.
Reimers, N. and Gurevych, I. (2019). Sentence-bert: Sentence embeddings using siamese bert-networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics.
Savić, M., Ivanović, M., Radovanović, M., Ognjanović, Z., Pejović, A., and Jakšić Krüger, T. (2015). ICT Innovations 2014: World of Data, chapter Exploratory Analysis of Communities in Co-authorship Networks: A Case Study, pages 55–64. Springer International Publishing, Cham.
Tang, L. and Liu, H. (2010). Community Detection and Mining in Social Media. Morgan and Claypool, New York, USA.
Tang, L., Wang, X., and Liu, H. (2011). Group profiling for understanding social structures. ACM Trans. Intell. Syst. Technol., 3(1).
Wang, Q., Erqsous, M., Barner, K. E., and Mauriello, M. L. (2025). Lata: A pilot study on llm-assisted thematic analysis of online social network data generation experiences. Proc. ACM Hum.-Comput. Interact., 9(2).
Wasserman, S. and Faust, K. (1994). Social Network Analysis: methods and applications (structural analysis in the social sciences). Cambridge University Press, New York, USA.
Yin, M., Liu, H., Lian, B., and Cai, R. (2026). Copersona: Leveraging llms and expert collaboration to understand user personas through social media data analysis. Design for Augmented Humanity, 1(1):49–66.
Zhang, T., Kishore, V., Wu, F., Weinberger, K. Q., and Artzi, Y. (2020). Bertscore: Evaluating text generation with bert. In International Conference on Learning Representations.
Publicado
19/10/2026
Como Citar
SANTOS, Vinicius V.; OLIVEIRA, Hilário Tomaz Alves de; GOMES, João E. Ambrósio.
LLM-Based Summarization of Academic Communities Using Relational Group Characterization. In: ENCONTRO NACIONAL DE INTELIGÊNCIA ARTIFICIAL E COMPUTACIONAL (ENIAC), 23. , 2026, Cuiabá/MT.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 3071-3082.
ISSN 2763-9061.
DOI: https://doi.org/10.5753/eniac.2026.31093.
