Analítica multimodal del aprendizaje para la evaluación inclusiva: inteligencia artificial, comportamiento y nuevas métricas educativas
DOI:
https://doi.org/10.68503/y0qy5h09Keywords:
analítica multimodal del aprendizaje, evaluación inclusiva, inteligencia artificial, comportamiento, métricas educativasAbstract
La analítica multimodal del aprendizaje (MMLA) integra datos procedentes de múltiples fuentes registros digitales, audio, video, movimiento, posición, mirada y señales fisiológicas para comprender procesos educativos que no pueden representarse mediante una única métrica. Esta revisión narrativa tuvo como objetivo analizar, entre 2019 y 2023, las oportunidades y limitaciones de la MMLA apoyada por inteligencia artificial para una evaluación inclusiva, con especial atención a la interpretación del comportamiento, la validez de nuevas métricas, la retroalimentación y los riesgos éticos. Se integró evidencia sobre diseño de sistemas, fusión multimodal, evaluación formativa, aprendizaje colaborativo, simulación, privacidad, equidad e inteligencia artificial. Los resultados muestran que la MMLA puede ampliar la evaluación más allá de calificaciones y clics, haciendo visibles procesos espaciales, comunicativos y colaborativos y facilitando retroalimentación basada en evidencia. Sin embargo, la literatura continúa concentrada en educación superior, muestras reducidas y entornos experimentales; además, persisten problemas de generalización, transparencia, privacidad, consentimiento y posible confusión entre conducta observable y aprendizaje. Se concluye que una evaluación multimodal inclusiva requiere combinar métricas pedagógicamente válidas, inteligencia artificial interpretable, análisis desagregado, participación de estudiantes y docentes, minimización de datos y supervisión humana. Las nuevas métricas deben utilizarse para ampliar las formas de demostrar aprendizaje y no para imponer patrones conductuales únicos como norma de rendimiento.
References
1. Worsley M, Martinez-Maldonado R, D’Angelo C. A new era in multimodal learning analytics: twelve core commitments to ground and grow MMLA. J Learn Anal. 2021;8(3):10-27. https://doi.org/10.18608/jla.2021.7361.
2. Chejara P, Prieto LP, Ruiz-Calleja A, Rodríguez-Triana MJ, Shankar SK, Kasepalu R. EFAR-MMLA: an evaluation framework to assess and report generalizability of machine learning models in MMLA. Sensors. 2021;21(8):2863. https://doi.org/10.3390/s21082863.
3. Mangaroska K, Martinez-Maldonado R, Vesin B, Gašević D. Challenges and opportunities of multimodal data in human learning: the computer science students’ perspective. J Comput Assist Learn. 2021;37(4):1030-1047. https://doi.org/10.1111/jcal.12542.
4. Dominguez F, Ochoa X, Zambrano D, Camacho K, Castells J. Scaling and adopting a multimodal learning analytics application in an institution-wide setting. IEEE Trans Learn Technol. 2021;14(3):400-414. https://doi.org/10.1109/TLT.2021.3100778.
5. Chango W, Lara JA, Cerezo R, Romero C. A review on data fusion in multimodal learning analytics and educational data mining. WIREs Data Min Knowl Discov. 2022;12(4):e1458. https://doi.org/10.1002/widm.1458.
6. Ouhaichi H, Spikol D, Vogel B. Research trends in multimodal learning analytics: a systematic mapping study. Comput Educ Artif Intell. 2023;4:100136. https://doi.org/10.1016/j.caeai.2023.100136.
7. Yan L, Zhao L, Gašević D, Martinez-Maldonado R. Scalability, sustainability, and ethicality of multimodal learning analytics. In: LAK22: 12th International Learning Analytics and Knowledge Conference. New York: ACM; 2022. p.13-23. https://doi.org/10.1145/3506860.3506862
8. Yan L, Martinez-Maldonado R, Gallo Cordoba B, Deppeler J, Corrigan D, Gašević D. Mapping from proximity traces to socio-spatial behaviours and student progression at the school. Br J Educ Technol. 2022;53(6):1645-1664. https://doi.org/10.1111/bjet.13203.
9. Khalil M, Slade S, Prinsloo P. Learning analytics in support of inclusiveness and disabled students: a systematic review. J Comput High Educ. Published online March 14, 2023. https://doi.org/10.1007/s12528-023-09363-4
10. Baker RS, Hawn A. Algorithmic bias in education. Int J Artif Intell Educ. 2022;32:1052-1092. https://doi.org/10.1007/s40593-021-00285-9.
11. Deho OB, Zhan C, Li J, Liu J. How do the existing fairness metrics and unfairness mitigation algorithms contribute to ethical learning analytics? Br J Educ Technol. 2022;53. https://doi.org/10.1111/bjet.13217
12. Yan L, Martinez-Maldonado R, Zhao L, Dix S, Jaggard H, Wotherspoon R, et al. The role of indoor positioning analytics in assessment of simulation-based learning. Br J Educ Technol. 2023;54(1):267-292. https://doi.org/10.1111/bjet.13262.
13. Zhao L, Yan L, Gašević D, Dix S, Jaggard H, Wotherspoon R, et al. Modelling co-located team communication from voice detection and positioning data in healthcare simulation. In: LAK22. New York: ACM; 2022. p.370-380. https://doi.org/10.1145/3506860.3506935
14. Yan L, Martinez-Maldonado R, Zhao L, et al. How do teachers use open learning spaces? Mapping from teachers’ socio-spatial data to spatial pedagogy. In: LAK22. New York: ACM; 2022. p.87-97. https://doi.org/10.1145/3506860.3506872
15. Martinez-Maldonado R, Echeverria V, Fernandez-Nieto G, Yan L, Zhao L, Alfredo R, et al. Lessons learnt from a multimodal learning analytics deployment in-the-wild. ACM Trans Comput-Hum Interact. 2023;31(1):Article. 8. https://doi.org/10.1145/3622784.
16. Fernandez-Nieto GM, Echeverria V, Buckingham Shum S, Mangaroska K, Kitto K, Palominos E, et al. Storytelling with learner data: guiding student reflection on multimodal team data. IEEE Trans Learn Technol. 2021;14(5):695-708. https://doi.org/10.1109/TLT.2021.3131842.
17. Nasir J, Bruno B, Chetouani M, Dillenbourg P. What if social robots look for productive engagement? Automated assessment of goal-centric engagement in learning applications. Int J Soc Robot. 2022;14:55-71. https://doi.org/10.1007/s12369-021-00766-w.
18. Alwahaby H, Cukurova M, Papamitsiou Z, Giannakos M. The evidence of impact and ethical considerations of multimodal learning analytics: a systematic literature review. In: Giannakos M, Spikol D, Di Mitri D, Sharma K, Ochoa X, Hammad R, editors. The Multimodal Learning Analytics Handbook. Cham: Springer; 2022. p.289-325. https://doi.org/10.1007/978-3-031-08076-0_12
19. Liu Q, et al. Understanding privacy and data protection issues in learning analytics using a systematic review. Br J Educ Technol. 2023. https://doi.org/10.1111/bjet.13388
20. Prinsloo P, Slade S, Khalil M. Multimodal learning analytics—in-between student privacy and encroachment: a systematic review. Br J Educ Technol. 2023;54:1566-1586. https://doi.org/10.1111/bjet.13373.
21. Currier C. Unresolved privacy and ethics issues related to learning analytics in higher education and academic librarianship. Emerg Libr Inf Perspect. 2021;4(1). https://doi.org/10.5206/elip.v4i1.13463
22. Li W, Sun K, Schaub F, Brooks C. Disparities in students’ propensity to consent to learning analytics. Int J Artif Intell Educ. 2022;32(3):564-608. https://doi.org/10.1007/s40593-021-00254-2.
23. Ouyang F, Dai X, Chen S. Applying multimodal learning analytics to examine the immediate and delayed effects of instructor scaffoldings on small groups’ collaborative programming. Int J STEM Educ. 2022;9:45. https://doi.org/10.1186/s40594-022-00361-z.
24. Giannakos M, Spikol D, Di Mitri D, Sharma K, Ochoa X, Hammad R, editors. The Multimodal Learning Analytics Handbook. Cham: Springer; 2022. https://doi.org/10.1007/978-3-031-08076-0
25. Liao CH, Wu JY. Deploying multimodal learning analytics models to explore the impact of digital distraction and peer learning on student performance. Comput Educ. 2022;190:104599. https://doi.org/10.1016/j.compedu.2022.104599.
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Graciela Mamani Torres, Giovanni Juan Maldonado Aguirre, Wilson Ángel Gutiérrez Rodríguez (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
The article is distributed under the Creative Commons Attribution 4.0 License. Unless otherwise stated, associated published material is distributed under the same licence.
