Análisis de características de usuario con Machine Learning

Alberto Gaspar; José Ignacio Panach; Miriam Gil; Verónica Romero; Damiano Distante

doi:10.65234/interaccion.148

Autores/as

Alberto Gaspar Departament d’informàtica, Escola Tècnica Superior d’Enginyeria, Universitat de València https://orcid.org/0000-0002-9236-4391
José Ignacio Panach Departament d’informàtica, Escola Tècnica Superior d’Enginyeria, Universitat de València https://orcid.org/0000-0002-7043-6227
Miriam Gil Departament d’informàtica, Escola Tècnica Superior d’Enginyeria, Universitat de València https://orcid.org/0000-0002-2987-1825
Verónica Romero Departament d’informàtica, Escola Tècnica Superior d’Enginyeria, Universitat de València https://orcid.org/0000-0002-1721-5732
Damiano Distante Unitelma Sapienza University of Rome https://orcid.org/0000-0002-8467-535X

DOI:

https://doi.org/10.65234/interaccion.148

Palabras clave:

Interfaces Inteligentes de Usuario , Clasificación de Usuarios , Machine Learning , Interfaz gráfica de Usuario

Resumen

El diseño de interfaces inteligentes que se adaptan a las características del usuario es un factor clave para mejorar la experiencia de uso. Sin embargo, existe una carencia de estudios empíricos que comparen la extracción automática de características de usuario con la percepción que los propios usuarios tienen de dichas características. En este trabajo se evalúan cuatro algoritmos de aprendizaje automático para clasificar a los usuarios en función de su nivel de habilidad y conocimiento: Perceptrón Multicapa (MLP), Naive Bayes (NB), Máquina de Soporte Vectorial (SVM) y Random Forest (RF). Estos algoritmos son adecuados para modelar relaciones complejas entre los datos de interacción y los perfiles de usuario. Los resultados muestran que MLP y SVM ofrecen el rendimiento más consistente en términos de precisión. No obstante, todos los modelos presentan dificultades para clasificar correctamente las clases minoritarias, especialmente en los usuarios con bajos niveles de habilidad y conocimiento.

Referencias

Abourobea, M., Atia, M., & Ismail, K. (2025). Comparative Study of Machine Learning Approaches for Fixed Radar-Based Road User Classification. 2025 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA), 1-6. https://doi.org/https://www.doi.org/10.1109/ACDSA65407.2025.11165993

Abri, S., Abri, R., & Çetin, S. (2020). A Classification on Different Aspects of User Modelling in Personalized Web Search. NLPIR 2020: 4th International Conference on Natural Language Processing and Information Retrieval, Seoul, Republic of Korea, December 18-20, 2020, 194-199. https://doi.org/https://doi.org/10.1145/3443279.3443291

Alruwais, N., & Zakariah, M. (2023). Evaluating Student Knowledge Assessment Using Machine Learning Techniques. Sustainability, 15(7). https://doi.org/10.3390/su15076229

Alwafi, G., & Fakieh, B. (2024). A machine learning model to predict privacy fatigued users from social media personalized advertisements. Scientific Reports, 14(1), 3685. https://doi.org/https://doi.org/10.1038/s41598-024-54078-w

Basuni, N. S., & Siregar, A. M. (2023). Comparison of the Accuracy of Drug User Classification Models Using Machine Learning Methods. Journal RESTI, 7(6), 1348-1358. https://doi.org/https://www.doi.org/10.29207/resti.v7i6.5401

Brusilovsky, P. (1996). Methods and techniques of adaptive hypermedia. En User Modeling and User-Adapted Interaction (Vol. 6, Número 2, pp. 87-129). https://doi.org/10.1007/BF00143964

Çetinkaya, A., Baykan, Ö. K., & Kırgız, H. (2023). Analysis of Machine Learning Classification Approaches for Predicting Students’ Programming Aptitude. Sustainability, 15(17). https://doi.org/10.3390/su151712917

Duan, S., Wang, Z., Wang, S., Chen, M., & Zhang, R. (2024). Emotion-Aware Interaction Design in Intelligent User Interface Using Multi-Modal Deep Learning. CoRR, abs/2411.06326. https://doi.org/10.48550/ARXIV.2411.06326

Gaspar, A., Gil, M., Panach, J. I., & Romero, V. (2024). Towards a general user model to develop intelligent user interfaces. Multim. Tools Appl., 83(26), 67501-67534. https://doi.org/https://doi.org/10.1007/s11042-024-18240-w

Gaspar, A., Panach Navarrete, J. I., Gil, M., Romero Gómez, V., & Distante, D. (2026). Análisis de Características de Usuario con Machine Learning: Material suplementario. Zenodo. https://doi.org/10.5281/ZENODO.20848896

Geraci, A., Katki, F., McMonegal, L., Meyer, B., Lane, J., Wilson, P., Radatz, J., Yee, M., Porteous, H., & Springsteel, F. (1991). IEEE Standard Computer Dictionary: Compilation of IEEE Standard Computer Glossaries. IEEE Press. https://doi.org/https://dl.acm.org/doi/abs/10.5555/574566

Jaber, A., & Csonka, B. (2023). Investigating the temporal differences among bike-sharing users through comparative analysis based on count, time series, and data mining models. Alexandria Engineering Journal, 77, 1-13. https://doi.org/https://doi.org/10.1016/j.aej.2023.06.087

Kadhim, A. I. (2019). Survey on supervised machine learning techniques for automatic text classification. Artificial Intelligence Review, 52(1), 273-292. https://doi.org/10.1007/s10462-018-09677-1

Kristić, M., Zakarija, I., Škopljanac-Mačina, F., & Car, Ž. (2025). Machine Learning for Adaptive Accessible User Interfaces: Overview and Applications. Applied Sciences, 15(23). https://doi.org/10.3390/app152312538

Manning, C. D., Raghavan, P., & Schütze, H. (2008). Introduction to information retrieval. Cambridge University Press. https://doi.org/10.1017/CBO9780511809071

Murphy, K. P. (2012). Machine learning—A probabilistic perspective. MIT Press.

Saranya, S., Malligeswari, N., Graf, F. T., & Murugan, V. (2025). Malicious user classification in cognitive 5G networks using novel improved bidirectional encoder representations from transformers model. Scientific Reports, 15(1), 43415. https://doi.org/https://doi.org/10.1038/s41598-025-19156-7

Schaible, M., Unger, H., Besier, A., & Mur, E. (2024). Adaptive Learning of User’s Interests. Proceedings of the 2023 7th International Conference on Natural Language Processing and Information Retrieval, NLPIR ’23, 261-265. https://doi.org/https://doi.org/10.1145/3639233.3639336

Shannaq, B. (2024). IMPROVING SECURITY IN IN℡LIGENT SYSTEMS: HOW EFFECTIVE ARE MACHINE LEARNING MODELS WITH TF-IDF VECTORIZATION FOR PASSWORD-BASED USER CLASSIFICATION. Journal of Theoretical and Applied Information Technology, 102(22), 8340-8355.

Siino, M., Di Nuovo, E., Tinnirello, I., & La Cascia, M. (2022). Fake News Spreaders Detection: Sometimes Attention Is Not All You Need. Information, 13(9). https://doi.org/https://www.doi.org/10.3390/info13090426

Tachie-Donkor, G., & Ezema, I. J. (2023). Effect of information literacy skills on university students’ information seeking behaviour and lifelong learning. Heliyon, 9(8), e18427. https://doi.org/https://doi.org/10.1016/j.heliyon.2023.e18427

Yuvapriya, P., Subramanian, P., & Surendran, R. (2025). Performance Analysis of Information Technology Professionals Using Optimal User Clustering and Machine Learning Model for Adaptive e-learning. 2025 8th International Conference on Trends in Electronics and Informatics (ICOEI), 1159-1165. https://doi.org/https://www.doi.org/10.1109/ICOEI65986.2025.11013491

Zahoor, K., & Bawany, N. Z. (2024). Explainable artificial intelligence approach towards classifying educational android app reviews using deep learning. Interact. Learn. Environ., 32(9), 5227-5252. https://doi.org/https://doi.org/10.1080/10494820.2023.2212708

Análisis de características de usuario con Machine Learning

Autores/as

DOI:

Palabras clave:

Resumen

Referencias

Descargas

Publicado

Número

Sección

Licencia