Article citationsMore>>

Andrade-Girón, D., Sandivar-Rosas, J., Marín-Rodriguez, W., Susanibar-Ramirez, E., Toro-Dextre, E., Ausejo-Sanchez, J. et al. (2023). Predicting Student Dropout Based on Machine Learning and Deep Learning: A Systematic Review. EAI Endorsed Transactions on Scalable Information Systems, 10, 1-11.
https://doi.org/10.4108/eetsis.3586

has been cited by the following article:

• TITLE: Archaic Methods in a Data Rich World: Why Educational Research Must Embrace AI Research Methods

  AUTHORS: Thomas Mgonja

  KEYWORDS: AI in Education, Machine Learning, Educational Research Methods, Causal Inference, Explainable AI

  JOURNAL NAME: Open Journal of Social Sciences, Vol.13 No.11, November 25, 2025

  ABSTRACT: Educational research stands at a crossroads that is both methodological and philosophical. The field must decide whether to remain anchored in a toolkit built for small samples and linear assumptions or to integrate approaches suited to high dimensional, complex, and nonlinear data. This commentary argues for methodological bilingualism that combines the strengths of established quantitative, qualitative, and mixed traditions with advances in machine learning and modern causal inference. The commentary reviews literature on learning analytics and AI in education, highlights developments in causal machine learning and model interpretability, and examines the political economy of data that shapes what counts as robust evidence. The commentary ultimately asks whether educational researchers will lead the integration of AI methods in ways that uphold justice and rigor, or whether they will cede authority to corporate actors who define the future of learning on their own terms.