Modelos preditivos baseados no uso de analítica da aprendizagem no ensino superior

uma revisão sistemática

Autores

  • Javier Mella-Norambuena Universidad Católica de la Santísima Concepción, Programa de Doctorado en Educación, Concepción, Chile / Universidad Técnica Federico Santa María, Departamento de Ciencias, Concepción, Chile https://orcid.org/0000-0002-4288-142X
  • María Graciela Badilla-Quintana Universidad Católica de la Santísima Concepción, Centro de Investigación en Educación y Desarrollo, Concepción, Chile https://orcid.org/0000-0002-1317-9228
  • Yaranay López Angulo Universidad Santo Tomás, Facultad de Ciencias Sociales y Comunicaciones, Escuela de Psicología, Concepción, Chile / Universidad de Concepción, Departamento de Psicología, Facultad de Ciencias Sociales, Concepción, Chile https://orcid.org/0000-0002-3331-6875

DOI:

https://doi.org/10.35699/1983-3652.2022.36310

Palavras-chave:

Modelo preditivo, Analítica da aprendizagem, Educação superior, Revisão sistemática

Resumo

Os métodos tradicionais de previsão de risco acadêmico às vezes apresentam limitações para identificação oportuna. Por outro lado, a Analítica da Aprendizagem (Learning Analytics) apresenta certas vantagens. O objetivo deste estudo é analisar características de modelos preditivos baseados na análise da aprendizagem no Ensino Superior. Uma revisão sistemática dos bancos de dados Web of Science, Scopus e Eric foi conduzida usando as palavras-chave "análise de aprendizagem" e "predição". Foram selecionados doze estudos de pesquisa que preenchiam os critérios de inclusão. Os resultados indicam que 100% dos estudos buscaram prever o desempenho acadêmico, incluindo variáveis analíticas, sociodemográficas e sociocognitivas como preditores. O sistema de gerenciamento de aprendizagem mais comumente utilizado foi o Moodle para aprendizagem combinada e cursos on-line. Os estudos foram realizados principalmente na Europa, sendo as amostras de até 500 participantes de Engenharia e Tecnologia. O tipo de análise mais frequente foi a regressão nos softwares R e SPSS. A maioria conseguiu um grande modelo de previsão (R2 > .30). Conclui-se que a atual construção de modelos de previsão de abandono escolar tem limitações importantes.

Downloads

Não há dados estatísticos.

Referências

AKÇAPINAR, Gökhan; ALTUN, Arif y AŞKAR, Petek. Using learning analytics to develop early-warning system for at-risk students. International Journal of Educational Technology in Higher Education, v. 16, n. 1, pág. 40, dic. 2019. DOI: 10.1186/s41239-019-0172-z. Disponible en: https://educationaltechnologyjournal.springeropen.com/articles/10.1186/s41239-019-0172-z. Acceso en: 27 ene. 2022.

BANIHASHEM, Seyyed Kazem y col. Learning Analytics: A Systematic Literature Review. Interdisciplinary Journal of Virtual Learning in Medical Sciences, v. 9, n. 2, jun. 2018. ISSN 2476-7263, 2476-7271. DOI: 10.5812/ijvlms.63024. Disponible en: http://ijvlms.com/en/articles/63024.html. Acceso en: 27 ene. 2022.

BANSAL, Anmol y SRIVASTAVA, Satyajee. Tools Used in Data Analysis: A Comparative Study. International Journal of Recent Research, v. 5, n. 1, p. 15-18, 2018. Disponible en: https://www.ijrra.net/Vol5issue1/IJRRA-05-01-04.pdf.

CECHINEL, Cristian y col. Mapping Learning Analytics initiatives in Latin America. British Journal of Educational Technology, v. 51, n. 4, p. 892-914, jul. 2020. DOI: 10.1111/bjet.12941. Disponible en: https://onlinelibrary.wiley.com/doi/10.1111/bjet.12941. Acceso en: 27 ene. 2022.

COLLIAU, Taylor y col. MatLab vs. Python vs. R. Journal of Data Science, v. 15, n. 3, p. 355-372, mar. 2021. DOI: 10.6339/JDS.201707_15(3).0001. Disponible en: https://jds-online.org/journal/JDS/article/402. Acceso en: 27 ene. 2022.

CONIJN, Rianne y col. Predicting Student Performance from LMS Data: A Comparison of 17 Blended Courses Using Moodle LMS. IEEE Transactions on Learning Technologies, v. 10, n. 1, p. 17-29, ene. 2017. DOI: 10.1109/TLT.2016.2616312. Disponible en: http://ieeexplore.ieee.org/document/7589022/. Acceso en: 27 ene. 2022.

DOBRE, Iuliana. Learning Management Systems for Higher Education - An Overview of Available Options for Higher Education Organizations. Procedia - Social and Behavioral Sciences, v. 180, n. 1, p. 313-320, mayo 2015. DOI: 10.1016/j.sbspro.2015.02.122. Disponible en: https://linkinghub.elsevier.com/retrieve/pii/S1877042815014536. Acceso en: 27 ene. 2022.

GAŠEVIĆ, Dragan y col. Learning analytics should not promote one size fits all: The effects of instructional conditions in predicting academic success. The Internet and Higher Education, v. 28, p. 68-84, ene. 2016. DOI: 10.1016/j.iheduc.2015.10.002. Disponible en: https://linkinghub.elsevier.com/retrieve/pii/S1096751615300038. Acceso en: 27 ene. 2022.

GUERRA, Julio y col. Adaptation and evaluation of a learning analytics dashboard to improve academic support at three Latin American universities. British Journal of Educational Technology, v. 51, n. 4, p. 973-1001, jul. 2020. DOI: 10.1111/bjet.12950. Disponible en: https://onlinelibrary.wiley.com/doi/10.1111/bjet.12950. Acceso en: 27 ene. 2022.

HOODA, Monika. Learning Analytics Lens: Improving Quality of Higher Education. International Journal of Emerging Trends in Engineering Research, v. 8, n. 5, p. 1626-1646, mayo 2020. DOI: 10.30534/ijeter/2020/24852020. Disponible en: http://www.warse.org/IJETER/static/pdf/file/ijeter24852020.pdf. Acceso en: 27 ene. 2022.

IFENTHALER, Dirk y YAU, Jane Yin-Kim. Reflections on Different Learning Analytics Indicators for Supporting Study Success. International Journal of Learning Analytics and Artificial Intelligence for Education (iJAI), v. 2, n. 2, pág. 4, jul. 2020. DOI: 10.3991/ijai.v2i2.15639. Disponible en: https://online-journals.org/index.php/i-jai/article/view/15639. Acceso en: 27 ene. 2022.

IFENTHALER, Dirk y YAU, Jane Yin-Kim. Utilising learning analytics to support study success in higher education: a systematic review. Educational Technology Research and Development, v. 68, n. 4, p. 1961-1990, ago. 2020. DOI: 10.1007/s11423-020-09788-z. Disponible en: https://link.springer.com/10.1007/s11423-020-09788-z. Acceso en: 27 ene. 2022.

KADIR, Aini Zuriyati Abdul y AZIZ, Nur Sukinah. Learning Management System of Higher Education Institution. Indian Journal of Science and Technology, v. 9, n. 9, mar. 2016. ISSN 0974-5645, 0974-6846. DOI: 10.17485/ijst/2016/v9i9/88717. Disponible en: https://indjst.org/articles/learning-management-system-of-higher-education-institution. Acceso en: 27 ene.

KASIM, Nurul Nadirah y KHALID, Fariza. Choosing the Right Learning Management System (LMS) for the Higher Education Institution Context: A Systematic Review. International Journal of Emerging Technologies in Learning (iJET), v. 11, n. 06, pág. 55, jun. 2016. DOI: 10.3991/ijet.v11i06.5644. Disponible en: http://online-journals.org/index.php/i-jet/article/view/5644. Acceso en: 27 ene. 2022.

KERIMBAYEV, Nurassyl y col. Virtual educational environment: interactive communication using LMS Moodle. Education and Information Technologies, v. 25, n. 3, p. 1965-1982, mayo 2020. DOI: 10.1007/s10639-019-10067-5. Disponible en: http://link.springer.com/10.1007/s10639-019-10067-5. Acceso en: 27 ene. 2022.

KLAŠNJA-MILIĆEVIĆ, Aleksandra; IVANOVIĆ, Mirjana y BUDIMAC, Zoran. Data science in education: Big data and learning analytics. Computer Applications in Engineering Education, v. 25, n. 6, p. 1066-1078, nov. 2017. DOI: 10.1002/cae.21844. Disponible en: https://onlinelibrary.wiley.com/doi/10.1002/cae.21844. Acceso en: 27 ene. 2022.

LARRABEE, Anders; HUGHES, Emily y SMITH, Joanne. The efficacy of learning analytics interventions in higher education: A systematic review. British Journal of Educational Technology, v. 50, n. 5, p. 2594-2618, sep. 2019. DOI: 10.1111/bjet.12720. Disponible en: https://onlinelibrary.wiley.com/doi/10.1111/bjet.12720. Acceso en: 27 ene. 2022.

LÁZARO ALVAREZ, Niurys; CALLEJAS, Zoraida y GRIOL, David. Predicting Computer Engineering students’ dropout in Cuban Higher Education with pre-enrollment and early performance data. Journal of Technology and Science Education, v. 10, n. 2, pág. 241, sep. 2020. DOI: 10.3926/jotse.922. Disponible en: https://www.jotse.org/index.php/jotse/article/view/922. Acceso en: 27 ene. 2022.

LU, Owen H. T. y col. Applying Learning Analytics for the Early Prediction of Students’ Academic Performance in Blended Learning. Educational Technology & Society, v. 21, n. 2, p. 220-232, 2018. Disponible en: https://eric.ed.gov/?id=EJ1175301. Acceso en: 27 ene. 2022.

LUSIGI, Angela. Higher Education, Technology, and Equity in Africa. New Review of Information Networking, v. 24, n. 1, p. 1-16, ene. 2019. DOI: 10.1080/13614576.2019.1608576. Disponible en: https://www.tandfonline.com/doi/full/10.1080/13614576.2019.1608576. Acceso en: 27 ene. 2022.

MIRANDA, Sergio y VEGLIANTE, Rosa. Learning Analytics to support learners and teachers: the navigation among contents as a model to adopt. Journal of e-Learning and Knowledge Society, p. 101-116, oct. 2019. DOI: 10.20368/1971-8829/1135065. Disponible en: https://www.je-lks.org/ojs/index.php/Je-LKS_EN/article/view/1135065. Acceso en: 27 ene. 2022.

MITTELMEIER, Jenna y col. Learning design in diverse institutional and cultural contexts: suggestions from a participatory workshop with higher education professionals in Africa. Open Learning: The Journal of Open, Distance and e-Learning, v. 33, n. 3, p. 250-266, sep. 2018. DOI: 10.1080/02680513.2018.1486185. Disponible en: https://www.tandfonline.com/doi/full/10.1080/02680513.2018.1486185. Acceso en: 27 ene. 2022.

MOHER, David y col. Preferred reporting items for systematic review and meta-analysis protocols (PRISMA-P) 2015 statement. Systematic Reviews, v. 4, n. 1, pág. 1, dic. 2015. DOI: 10.1186/2046-4053-4-1. Disponible en: https://systematicreviewsjournal.biomedcentral.com/articles/10.1186/2046-4053-4-1. Acceso en: 27 ene. 2022.

MONLLAÓ OLIVÉ, David y col. A supervised learning framework: using assessment to identify students at risk of dropping out of a MOOC. Journal of Computing in Higher Education, v. 32, n. 1, p. 9-26, abr. 2020. DOI: 10.1007/s12528-019-09230-1. Disponible en: http://link.springer.com/10.1007/s12528-019-09230-1. Acceso en: 27 ene. 2022.

MUBARAK, Ahmed Ali; CAO, Han y AHMED, Salah A.M. Predictive learning analytics using deep learning model in MOOCs’ courses videos. Education and Information Technologies, v. 26, n. 1, p. 371-392, ene. 2021. DOI: 10.1007/s10639-020-10273-6. Disponible en: https://link.springer.com/10.1007/s10639-020-10273-6. Acceso en: 27 ene. 2022.

NGUYEN, Andy y col. Design principles for learning analytics information systems in higher education. European Journal of Information Systems, v. 30, n. 5, p. 541-568, sep. 2021. DOI: 10.1080/0960085X.2020.1816144. Disponible en: https://www.tandfonline.com/doi/full/10.1080/0960085X.2020.1816144. Acceso en: 27 ene. 2022.

PICCIANO, Anthony G. The Evolution of Big Data and Learning Analytics in American Higher Education. Online Learning, v. 16, n. 3, jun. 2012. DOI: 10.24059/olj.v16i3.267. Disponible en: https://olj.onlinelearningconsortium.org/index.php/olj/article/view/267. Acceso en: 27 ene. 2022.

PRIYAADHARSHINI, M y col. Learning Analytics: Game-based Learning for Programming Course in Higher Education. Procedia Computer Science, v. 172, p. 468-472, 2020. DOI: 10.1016/j.procs.2020.05.143. Disponible en: https://linkinghub.elsevier.com/retrieve/pii/S1877050920314733. Acceso en: 27 ene. 2022.

ROJAS CASTRO, Pablo. Learning Analytics. Una Revisión de la Literatura. Educación y Educadores, v. 20, n. 1, p. 106-128, feb. 2017. DOI: 10.5294/edu.2017.20.1.6. Disponible en: http://educacionyeducadores.unisabana.edu.co/index.php/eye/article/view/6412/4454. Acceso en: 27 ene. 2022.

ŞAHIN, Muhittin y YURDUGÜL, Halil. Educational Data Mining and Learning Analytics: Past, Present and Future. Bartın University Journal of Faculty of Education, v. 9, n. 1, p. 121-131, 2019.

SAIZ MANZANARES, María Consuelo y col. Detección del alumno en riesgo en titulaciones de Ciencias de la Salud: aplicación de técnicas de Learning Analytics. European Journal of Investigation in Health, Psychology and Education, v. 8, n. 3, pág. 129, dic. 2018. DOI: 10.30552/ejihpe.v8i3.273. Disponible en: https://formacionasunivep.com/ejihpe/index.php/journal/article/view/273. Acceso en: 27 ene. 2022.

SALGADO, Nelson y col. Modelo para predecir el rendimiento académico basado en redes neuronales y analítica de aprendizaje. Sistemas y Tecnologías de Información, v. 1, n. 17, p. 258-266, 2019.

SAQR, Mohammed; FORS, Uno y NOURI, Jalal. Time to focus on the temporal dimension of learning: a learning analytics study of the temporal patterns of students’ interactions and self-regulation. International Journal of Technology Enhanced Learning, v. 11, n. 4, pág. 398, 2019. DOI: 10.1504/IJTEL.2019.10020597. Disponible en: http://www.inderscience.com/link.php?id=10020597. Acceso en: 27 ene. 2022.

SOFFER, Tal y COHEN, Anat. Students’ engagement characteristics predict success and completion of online courses. Journal of Computer Assisted Learning, v. 35, n. 3, p. 378-389, jun. 2019. DOI: 10.1111/jcal.12340. Disponible en: https://onlinelibrary.wiley.com/doi/10.1111/jcal.12340. Acceso en: 27 ene. 2022.

SRIMADHAVEN, T. y col. Learning Analytics: Virtual Reality for Programming Course in Higher Education. Procedia Computer Science, v. 172, p. 433-437, 2020. DOI: 10.1016/j.procs.2020.05.095. Disponible en: https://linkinghub.elsevier.com/retrieve/pii/S1877050920314241. Acceso en: 27 ene. 2022.

STRANG, Kenneth David. Can online student performance be forecasted by learning analytics? International Journal of Technology Enhanced Learning, v. 8, n. 1, pág. 26, 2016. DOI: 10.1504/IJTEL.2016.075950. Disponible en: http://www.inderscience.com/link.php?id=75950. Acceso en: 27 ene. 2022.

TEMPELAAR, Dirk; RIENTIES, Bart y NGUYEN, Quan. Subjective data, objective data and the role of bias in predictive modelling: Lessons from a dispositional learning analytics application. Edición: Vitomir Kovanovic. PLOS ONE, v. 15, n. 6, e0233977, jun. 2020. DOI: 10.1371/journal.pone.0233977. Disponible en: https://dx.plos.org/10.1371/journal.pone.0233977. Acceso en: 27 ene. 2022.

TEMPELAAR, Dirk T.; RIENTIES, Bart y NGUYEN, Quan. Towards Actionable Learning Analytics Using Dispositions. IEEE Transactions on Learning Technologies, v. 10, n. 1, p. 6-16, ene. 2017. DOI: 10.1109/TLT.2017.2662679. Disponible en: http://ieeexplore.ieee.org/document/7839177/. Acceso en: 27 ene. 2022.

TULASI, Ben. Significance of Big Data and Analytics in Higher Education. In: BIG Data and Learning Analytics in Higher Education: Current Theory and Practice. Cham: Springer International Publishing, 2013. Disponible en: https://doi.org/10.1007/978-3-319-06520-5_1. Acceso en: 27 ene. 2022.

WIBAWA, Basuki y col. Learning analytic and educational data mining for learning science and technology. In: TRANSFORMING Research and Education of Science and Mathematics in the Digital Age. Jakarta, Indonesia: [s.n.], 2021. v. 20, pág. 060001. DOI: 10.1063/5.0041844. Disponible en: http://aip.scitation.org/doi/abs/10.1063/5.0041844. Acceso en: 27 ene. 2022.

ZABOLOTNIAIA, Mariia y col. Use of the LMS Moodle for an Effective Implementation of an Innovative Policy in Higher Educational Institutions. International Journal of Emerging Technologies in Learning (iJET), v. 15, n. 13, pág. 172, jul. 2020. DOI: 10.3991/ijet.v15i13.14945. Disponible en: https://online-journals.org/index.php/i-jet/article/view/14945. Acceso en: 27 ene. 2022.

ZHANG, Yaqun; GHANDOUR, Ahmad y SHESTAK, Viktor. Using Learning Analytics to Predict Students Performance in Moodle LMS. International Journal of Emerging Technologies in Learning (iJET), v. 15, n. 20, pág. 102, oct. 2020. DOI: 10.3991/ijet.v15i20.15915. Disponible en: https://online-journals.org/index.php/i-jet/article/view/15915. Acceso en: 27 ene. 2022.

ZHENG, Juan y col. Profiling self-regulation behaviors in STEM learning of engineering design. Computers & Education, v. 143, pág. 103669, ene. 2020. DOI: 10.1016/j.compedu.2019.103669. Disponible en: https://linkinghub.elsevier.com/retrieve/pii/S0360131519302222. Acceso en: 27 ene. 2022.

ZULKIFLI, Faiz; MOHAMED, Zulkifley y AZMEE, Nor Afzalina. Systematic Research on Predictive Models on Students’ Academic Performance in Higher Education. International Journal of Recent Technology and Engineering, v. 8, 2S3, p. 357-363, ago. 2019. DOI: 10.35940/ijrte.B1061.0782S319. Disponible en: https://www.ijrte.org/wp-content/uploads/papers/v8i2S3/B10610782S319.pdf. Acceso en: 27 ene. 2022.

Publicado

02-02-2022

Como Citar

MELLA-NORAMBUENA, J.; BADILLA-QUINTANA, M. G.; LÓPEZ ANGULO, Y. Modelos preditivos baseados no uso de analítica da aprendizagem no ensino superior: uma revisão sistemática. Texto Livre, Belo Horizonte-MG, v. 15, p. e36310, 2022. DOI: 10.35699/1983-3652.2022.36310. Disponível em: https://periodicos.ufmg.br/index.php/textolivre/article/view/36310. Acesso em: 28 mar. 2024.

Artigos mais lidos pelo mesmo(s) autor(es)