Integrating Game Learning Analytics and Local LLMs for Automated Interpretation of Player Behaviour in Games

  • Guilherme Silva UFABC
  • Íris Campanella UFABC
  • Júlia Pessoa UFABC
  • Karla Vittori UFABC
  • André L. Brandão UFABC

Resumo


Introduction: Digital games are valuable educational tools that generate interaction data for assessing student learning. However, analysing large volumes of gameplay logs remains challenging for educators due to their highly technical nature. Objective: This paper proposes an architecture that integrates Game Learning Analytics (GLA) with Large Language Models (LLMs) to automatically interpret player interactions in a serious game developed with Unity. Methodology: Player actions are captured using the GLA framework, generating structured logs that are analysed by a locally deployed LLM to produce natural-language reports. Preliminary Results: Initial tests show that the system can interpret player behaviour, identifying gameplay patterns, engagement characteristics, and potential conceptual difficulties without manual inspection of raw logs.
Palavras-chave: Serious Games, Game Learning Analytics, Large Language Models

Referências

Alonso-Fernández, C., Calvo-Morata, A., Freire, M., Martínez-Ortiz, I., and Fernández-Manjón, B. (2019). Applications of data science to game learning analytics data: A systematic literature review. Computers & Education, 141:103612.

Bastos, M., Honda, F., Lima, M., Pessoa, M., and Pires, F. (2025). How do llms analyze and interpret data from educational games? a study with gla experts. In Anais do XXXVI Simpósio Brasileiro de Informática na Educação (SBIE 2025), SBIE 2025, page 1318–1331. Sociedade Brasileira de Computação - SBC.

Calvo-Morata, A., Alonso-Fernandez, C., Freire-Moran, M., Martinez-Ortiz, I., and Fernandez-Manjon, B. (2019). Game learning analytics, facilitating the use of serious games in the class. IEEE Revista Iberoamericana de Tecnologias del Aprendizaje, 14(4):168–176.

Calvo-Morata, A., Alonso-Fernández, C., Santilario-Berthilier, J., Martínez-Ortiz, I., and Fernández-Manjón, B. (2025a). Learning analytics to guide serious game development: A case study using articoding. Computers, 14(4):122.

Calvo-Morata, A., Santilario-Berthilieres, J., Alonso-Fernández, C., Freire, M., Martínez-Ortiz, I., and Fernández-Manjón, B. (2025b). Full software support for game learning analytics. Learning Analytics Summer Institute Spain.

Connolly, T. M., Boyle, E. A., MacArthur, E., Hainey, T., and Boyle, J. M. (2012). A systematic literature review of empirical evidence on computer games and serious games. Computers & Education, 59(2):661–686.

Heinemann, B., Ehlenz, M., Görzen, S., and Schroeder, U. (2022). xapi made easy: A learning analytics infrastructure for interdisciplinary projects. International Journal of Online and Biomedical Engineering (iJOE), 18(14):99–113.

Ji, Z., Lee, N., Frieske, R., Yu, T., Su, D., Xu, Y., Ishii, E., Bang, Y. J., Madotto, A., and Fung, P. (2023). Survey of hallucination in natural language generation. ACM Comput. Surv., 55(12).

Liu, X., Wei, Z., Baker, R. S., Metcalf, S. J., Zhang, J., Barany, A., Slater, S., Swanson, L., and Gagnon, D. J. (2025). Integrating large language models and machine learning to detect struggle in educational games. In International Conference on Artificial Intelligence in Education, pages 398–405. Springer.

Melo, D., Júnior, R., Duarte, J., and Pires, F. (2018). Robô euroi: Estratégias matemáticas para desenvolver o pensamento computacional. In Anais dos Workshops do Congresso Brasileiro de Informática na Educação, page 242.

Ollama (2024). Ollama’s documentation. [link]. Accessed: March 2026.

Serrano-Laguna, Á., Martínez-Ortiz, I., Haag, J., Regan, D., Johnson, A., and Fernández-Manjón, B. (2017). Applying standards to systematize learning analytics in serious games. Computer Standards & Interfaces, 50:116–123.

Silva, D., Pires, F., Melo, R., and Pessoa, M. (2022). Glboard: um sistema para auxiliar na captura e análise de dados em jogos educacionais. In Anais Estendidos do XXI Simpósio Brasileiro de Jogos e Entretenimento Digital (SBGames Estendido 2022), SBGames Estendido 2022, page 959–968. Sociedade Brasileira de Computação.

Unity Technologies (2025). Unity real-time development platform. [link]. Accessed: March 16, 2026.

Yu, Z., Gao, M., and Wang, L. (2021). The effect of educational games on learning outcomes, student motivation, engagement and satisfaction. Journal of Educational Computing Research, 59(3):522–546.

Zeng, J., Parks, S., and Shang, J. (2020). To learn scientifically, effectively, and enjoyably: A review of educational games. Human Behavior and Emerging Technologies, 2:186–195.
Publicado
29/09/2026
SILVA, Guilherme; CAMPANELLA, Íris; PESSOA, Júlia; VITTORI, Karla; BRANDÃO, André L.. Integrating Game Learning Analytics and Local LLMs for Automated Interpretation of Player Behaviour in Games. In: TRILHA DE COMPUTAÇÃO – ARTIGOS CURTOS - SIMPÓSIO BRASILEIRO DE JOGOS E ENTRETENIMENTO DIGITAL (SBGAMES), 25. , 2026, Goiânia/GO. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2026 . p. 146-152. DOI: https://doi.org/10.5753/sbgames_estendido.2026.25638.