Electronic Journal of e-Learning

Machine Learning in Art Teacher Education: A Comparative Analysis and Student Perceptions

Botagoz Kystaubayeva — 2026-02-03

Amid the global push for digital transformation in higher education, there is a critical need for objective, scalable assessment tools in subjective disciplines like visual arts. Modern teacher education increasingly integrates intelligent technologies, yet the application of machine learning (ML) for formative assessment in art education remains underexplored. While ML offers scalable feedback, its capacity to evaluate subjective creativity remains contested. The study aims to examine the technical accuracy of a CNN-based model trained on a local dataset of 300 archived projects, compared to instructor evaluations, and to analyze how future teachers (N = 180) perceive algorithmic feedback in assessment contexts. A mixed-methods design was employed using a highly reliable survey instrument (Cronbach’s α = .925) and comparative scoring analysis across four key dimensions: Technique, Composition, Color, and Creativity. Results indicate that the model aligns strongly with human assessments on technical execution (r = .426, p < .001), and moderate alignment for Composition (r = .430, p < .001) and weaker alignment for Color (r = .327, p < .001), while correlations for Creativity were notably weaker (r = .181, p = .015), indicating persistent limitations in modeling abstract artistic intent. ANOVA results revealed that students’ digital literacy significantly predicts their trust in the system (F = 3.547, p = .031) and willingness to use it (F = 8.476, p < .001). Furthermore, discrepancy analysis indicated systematic divergence across proficiency levels, with the model exhibiting increasing underestimation for highly proficient students, particularly in cases involving stylistic deviation or non-standard cultural expression. The findings suggest that while the algorithm provides consistent, transparent scoring that enhances assessment literacy, it lacks the sensitivity to evaluate high-level originality due to standardization bias. This study contributes to the field by empirically demonstrating the "accuracy–creativity trade-off" in ML-based art assessment and by validating a hybrid assessment framework that balances algorithmic precision with pedagogical intuition. The study concludes that ML tools should function as "human-in-the-loop" support systems rather than autonomous graders, fostering critical reflection and digital competence in future educators.

From Intention to Reflection: Understanding Self-Directed Learning in the Use of Generative AI in Vietnam

Diep-Ngoc Le — 2026-02-06

This study extends the Theory of Planned Behavior (TPB) to explore how students’ behavioral intentions toward using generative artificial intelligence (GenAI) are associated with their reflective engagement and self-directed learning (SDL) in higher education. As GenAI tools such as ChatGPT increasingly mediate learning, understanding how learners’ intentions are linked to autonomous and reflective learning behaviors becomes essential. Data were collected from 149 first-year university students (predominantly female) in Vietnam who had prior experience with GenAI for academic purposes. Using Partial Least Squares Structural Equation Modeling (PLS-SEM), the study examined relationships among attitudes, subjective norms, perceived behavioral control, behavioral intention, actual use, reflection, and two dimensions of SDL, including intentional learning and self-management. The results reveal that attitudes and perceived behavioral control significantly predict students’ intentions and actual use of GenAI, whereas subjective norms have no significant effect. Behavioral engagement is positively associated with reflection and both dimensions of SDL, while reflection is positively related to intentional learning and self-management, confirming its mediating role within the proposed model linking motivation-related constructs with autonomous learning outcomes. These findings highlight reflection as a metacognitive mechanism that links students’ behavioral engagement with GenAI and their SDL-related outcomes. Theoretically, the study advances TPB by positioning reflection and SDL as outcome constructs within the proposed model, rather than fixed learner traits. Practically, it suggests that educators and institutions working with first-year university students or similar learner populations should integrate reflective activities and AI literacy into curricula to promote critical, ethical, and autonomous engagement with GenAI. Designing learning environments that position AI as a reflective partner, rather than merely a content generator, supports learners’ self-regulation and reflective engagement. Overall, this research contributes to understanding how intentional and reflective interaction with GenAI is associated with deeper and more autonomous learning of students among first-year university students in a GenAI-supported learning context.