Student Perception in AVALIA UFPA: A Hybrid Approach Using Topic Modeling and LLM-Based Automatic Labeling
Resumo
Extracting actionable insights from textual student feedback is critical for institutional improvement, but manual analysis becomes a cognitive bottleneck when scaled institution-wide semesterly. To address this, we propose an automated pipeline integrating topic modeling and Generative AI for theme extraction and semantic labeling. We compare LSA, LDA, NMF, and BERTopic, evaluating the Meta-Llama-3.1-8B-Instruct model for automated semantic labeling. Results highlight BERTopic’s capacity to capture exclusive latent dimensions, alongside Llama’s interpretability in generating contextually appropriate labels. This approach offers a viable pathway to convert unstructured feedback into strategic intelligence, potentially facilitating educational management.Referências
Almeida, T., Barbosa, K., Fernandes, S., and Aquino, A. (2025). Topic modeling in feminist debates on instagram: A generative ai approach. In Anais do XIV Brazilian Workshop on Social Network Analysis and Mining, pages 173–186, Porto Alegre, RS, Brasil. SBC.
Bianchi, F., Terragni, S., and Hovy, D. (2021). Pre-training is a hot topic: Contextualized document embeddings improve topic coherence. In Zong, C., Xia, F., Li, W., and Navigli, R., editors, Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 759–766, Online. Association for Computational Linguistics.
Blei, D. M., Ng, A. Y., and Jordan, M. I. (2003). Latent dirichlet allocation. J. Mach. Learn. Res., 3(null):993–1022.
Blondel, V. D., Guillaume, J.-L., Lambiotte, R., and Lefebvre, E. (2008). Fast unfolding of communities in large networks. Journal of Statistical Mechanics: Theory and Experiment, 2008(10):P10008.
Chang, J., Boyd-Graber, J., Gerrish, S., Wang, C., and Blei, D. M. (2009). Reading tea leaves: how humans interpret topic models. In Proceedings of the 23rd International Conference on Neural Information Processing Systems, NIPS’09, page 288–296, Red Hook, NY, USA. Curran Associates Inc.
Deerwester, S., Dumais, S. T., Furnas, G. W., Landauer, T. K., and Harshman, R. (1990). Indexing by latent semantic analysis. Journal of the American Society for Information Science, 41(6):391–407.
Dieng, A. B., Ruiz, F. J. R., and Blei, D. M. (2019). Topic modeling in embedding spaces.
Fayyad, U., Piatetsky-Shapiro, G., and Smyth, P. (1996). From data mining to knowledge discovery in databases. AI Mag., 17(3):37–54.
Grootendorst, M. (2022). Bertopic: Neural topic modeling with a class-based tf-idf procedure.
Hammami, E. and Faiz, R. (2022). Text clustering based on multi-view representations. In CIRCLE.
Hayat, F., Shatnawi, S., and Haig, E. (2024). Comparative analysis of topic modelling approaches on student feedback. In Proceedings of the 16th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - KDIR, pages 226–233. INSTICC, SciTePress.
Kafiabad, S. T., Schiffauerova, A., and Ebadi, A. (2025). Decoding funded research: Comparative analysis of topic models and uncovering the effect of gender and geographic location.
Kardam, N. and Wilson, D. (2024). A hybrid approach to natural language processing for analyzing student feedback about faculty support. In 2024 ASEE Annual Conference & Exposition, number 10.18260/1-2–46447, Portland, Oregon. ASEE Conferences. [link].
Khandelwal, T. (2025). Using llm-based approaches to enhance and automate topic labeling.
Lee, D. D. and Seung, H. S. (1999). Learning the parts of objects by non-negative matrix factorization. nature, 401(6755):788–791.
Myftaraj, E., Fata, I., and Plasari, E. (2025). A topic modeling analysis of circular economy and big data research using bertopic and scibert. International Journal of Innovative Technology and Interdisciplinary Sciences, 8(4):1195–1243.
Neha Kardam, D. W. and Makhsous, S. (2024). A comparative analysis of natural language processing techniques for analyzing student feedback about ta support. In 2024 ASEE Annual Conference & Exposition, number 10.18260/1-2–46425, Portland, Oregon. ASEE Conferences. [link].
Piper, A. and Wu, S. (2025). Evaluating large language models for narrative topic labeling. In Hämäläinen, M., Öhman, E., Bizzoni, Y., Miyagawa, S., and Alnajjar, K., editors, Proceedings of the 5th International Conference on Natural Language Processing for Digital Humanities, pages 281–291, Albuquerque, USA. Association for Computational Linguistics.
Rijcken, E., Scheepers, F., Zervanou, K., Spruit, M., Mosteiro, P., and Kaymak, U. (2023). Towards interpreting topic models with chatgpt. The 20th World Congress of the International Fuzzy Systems Association, IFSA ; Conference date: 20-08-2023 Through 24-08-2023.
Röder, M., Both, A., and Hinneburg, A. (2015). Exploring the space of topic coherence measures. In Proceedings of the Eighth ACM International Conference on Web Search and Data Mining, WSDM ’15, page 399–408, New York, NY, USA. Association for Computing Machinery.
Salton, G., Wong, A., and Yang, C. S. (1975). A vector space model for automatic indexing. Commun. ACM, 18(11):613–620.
Vieira de Sousa, J., Maffini Griboski, C., and Woiciechowski Batista Gumesson, D. (2024). Autoavaliação institucional no marco do sinaes: movimentos e tensões no uso dos resultados para a qualidade da educação superior : Institutional self-assessment in the sinaes framework: movements and tensions in the use of results for the quality of higher education. Revista Cocar, (29).
Wanna, S., Barron, R., Solovyev, N., Eren, M. E., Bhattarai, M., Rasmussen, K., and Alexandrov, B. S. (2024). Topictag: Automatic annotation of nmf topic models using chain of thought and prompt tuning with llms.
Webber, W., Moffat, A., and Zobel, J. (2010). A similarity measure for indefinite rankings. ACM Trans. Inf. Syst., 28(4).
Zankadi, H., Idrissi, A., Daoudi, N., and Hilal, I. (2023). Identifying learners’ topical interests from social media content to enrich their course preferences in moocs using topic modeling and nlp techniques. Education and information technologies, 28(5):5567–5584.
Bianchi, F., Terragni, S., and Hovy, D. (2021). Pre-training is a hot topic: Contextualized document embeddings improve topic coherence. In Zong, C., Xia, F., Li, W., and Navigli, R., editors, Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 759–766, Online. Association for Computational Linguistics.
Blei, D. M., Ng, A. Y., and Jordan, M. I. (2003). Latent dirichlet allocation. J. Mach. Learn. Res., 3(null):993–1022.
Blondel, V. D., Guillaume, J.-L., Lambiotte, R., and Lefebvre, E. (2008). Fast unfolding of communities in large networks. Journal of Statistical Mechanics: Theory and Experiment, 2008(10):P10008.
Chang, J., Boyd-Graber, J., Gerrish, S., Wang, C., and Blei, D. M. (2009). Reading tea leaves: how humans interpret topic models. In Proceedings of the 23rd International Conference on Neural Information Processing Systems, NIPS’09, page 288–296, Red Hook, NY, USA. Curran Associates Inc.
Deerwester, S., Dumais, S. T., Furnas, G. W., Landauer, T. K., and Harshman, R. (1990). Indexing by latent semantic analysis. Journal of the American Society for Information Science, 41(6):391–407.
Dieng, A. B., Ruiz, F. J. R., and Blei, D. M. (2019). Topic modeling in embedding spaces.
Fayyad, U., Piatetsky-Shapiro, G., and Smyth, P. (1996). From data mining to knowledge discovery in databases. AI Mag., 17(3):37–54.
Grootendorst, M. (2022). Bertopic: Neural topic modeling with a class-based tf-idf procedure.
Hammami, E. and Faiz, R. (2022). Text clustering based on multi-view representations. In CIRCLE.
Hayat, F., Shatnawi, S., and Haig, E. (2024). Comparative analysis of topic modelling approaches on student feedback. In Proceedings of the 16th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - KDIR, pages 226–233. INSTICC, SciTePress.
Kafiabad, S. T., Schiffauerova, A., and Ebadi, A. (2025). Decoding funded research: Comparative analysis of topic models and uncovering the effect of gender and geographic location.
Kardam, N. and Wilson, D. (2024). A hybrid approach to natural language processing for analyzing student feedback about faculty support. In 2024 ASEE Annual Conference & Exposition, number 10.18260/1-2–46447, Portland, Oregon. ASEE Conferences. [link].
Khandelwal, T. (2025). Using llm-based approaches to enhance and automate topic labeling.
Lee, D. D. and Seung, H. S. (1999). Learning the parts of objects by non-negative matrix factorization. nature, 401(6755):788–791.
Myftaraj, E., Fata, I., and Plasari, E. (2025). A topic modeling analysis of circular economy and big data research using bertopic and scibert. International Journal of Innovative Technology and Interdisciplinary Sciences, 8(4):1195–1243.
Neha Kardam, D. W. and Makhsous, S. (2024). A comparative analysis of natural language processing techniques for analyzing student feedback about ta support. In 2024 ASEE Annual Conference & Exposition, number 10.18260/1-2–46425, Portland, Oregon. ASEE Conferences. [link].
Piper, A. and Wu, S. (2025). Evaluating large language models for narrative topic labeling. In Hämäläinen, M., Öhman, E., Bizzoni, Y., Miyagawa, S., and Alnajjar, K., editors, Proceedings of the 5th International Conference on Natural Language Processing for Digital Humanities, pages 281–291, Albuquerque, USA. Association for Computational Linguistics.
Rijcken, E., Scheepers, F., Zervanou, K., Spruit, M., Mosteiro, P., and Kaymak, U. (2023). Towards interpreting topic models with chatgpt. The 20th World Congress of the International Fuzzy Systems Association, IFSA ; Conference date: 20-08-2023 Through 24-08-2023.
Röder, M., Both, A., and Hinneburg, A. (2015). Exploring the space of topic coherence measures. In Proceedings of the Eighth ACM International Conference on Web Search and Data Mining, WSDM ’15, page 399–408, New York, NY, USA. Association for Computing Machinery.
Salton, G., Wong, A., and Yang, C. S. (1975). A vector space model for automatic indexing. Commun. ACM, 18(11):613–620.
Vieira de Sousa, J., Maffini Griboski, C., and Woiciechowski Batista Gumesson, D. (2024). Autoavaliação institucional no marco do sinaes: movimentos e tensões no uso dos resultados para a qualidade da educação superior : Institutional self-assessment in the sinaes framework: movements and tensions in the use of results for the quality of higher education. Revista Cocar, (29).
Wanna, S., Barron, R., Solovyev, N., Eren, M. E., Bhattarai, M., Rasmussen, K., and Alexandrov, B. S. (2024). Topictag: Automatic annotation of nmf topic models using chain of thought and prompt tuning with llms.
Webber, W., Moffat, A., and Zobel, J. (2010). A similarity measure for indefinite rankings. ACM Trans. Inf. Syst., 28(4).
Zankadi, H., Idrissi, A., Daoudi, N., and Hilal, I. (2023). Identifying learners’ topical interests from social media content to enrich their course preferences in moocs using topic modeling and nlp techniques. Education and information technologies, 28(5):5567–5584.
Publicado
19/10/2026
Como Citar
BRITO, Paula Manoella M. de; SOUZA, Samara L. de; SANTOS FILHO, Reginaldo C. dos.
Student Perception in AVALIA UFPA: A Hybrid Approach Using Topic Modeling and LLM-Based Automatic Labeling. In: ENCONTRO NACIONAL DE INTELIGÊNCIA ARTIFICIAL E COMPUTACIONAL (ENIAC), 23. , 2026, Cuiabá/MT.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 3641-3652.
ISSN 2763-9061.
DOI: https://doi.org/10.5753/eniac.2026.31492.
