EUVIMEDEUVIMED entdecken
MetaanalyseOpen Access · CC BY 4.0

Artificial intelligence and learner autonomy: a meta-analysis of self-regulated and self-directed learning

Krishnashree Achuthan

Frontiers in Education · 29.12.2025 · 10

DOI: 10.3389/feduc.2025.1738751 ↗

Kurz gefasst

Metaanalyse in der Zeitschrift Frontiers in Education, online erschienen am 29.12.2025. Verfasst von Krishnashree Achuthan. Die Arbeit wurde bisher 41-mal zitiert (Crossref) und nennt 81 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

As artificial intelligence (AI) becomes increasingly embedded in educational environments, understanding its role in shaping learners’ self-regulated learning (SRL) and self-directed learning (SDL) has emerged as a central concern in contemporary learning science. While prior studies suggest that AI-driven systems may support planning, monitoring, and autonomy in learning, empirical evidence remains fragmented across contexts, learner groups, and instructional designs. This study synthesizes existing empirical research to systematically examine the magnitude and conditions under which AI-based interventions influence SRL, its dimensions and phases, SDL, and associated learning outcomes.

Methods

A systematic meta-analysis was conducted following PRISMA guidelines, synthesizing evidence from 32 empirical studies comprising 92 effect sizes and a total of 3,029 participants. The analysis examined overall effects of AI-based interventions on SRL and SDL, disaggregated effects across SRL dimensions (cognitive/metacognitive, motivational/affective, and behavioral regulation) and SRL phases (forethought, performance, and self-reflection), as well as impacts on learning outcomes and academic achievement. Random-effects models were applied, and moderator analyses explored learner characteristics, contextual variables, and AI design features. Sensitivity analyses and publication bias assessments were performed to evaluate the robustness of findings.

Results

AI-based interventions demonstrated a large and statistically significant positive effect on overall SRL ( g = 1.613, p = 0.032) and SDL ( g = 1.111, p = 0.043), indicating substantial improvements in learners’ ability to plan, monitor, and regulate their learning while sustaining autonomy and persistence. At the dimensional level, AI produced moderate gains in cognitive/metacognitive regulation ( g = 0.377, p = 0.0004) and motivational/affective regulation ( g = 0.505, p = 0.013), whereas effects on behavioral regulation were inconsistent. Phase-level analyses revealed that AI interventions were most effective during the forethought phase, supporting goal setting, planning, and motivational readiness, with smaller but significant gains observed in self-reflection and variable effects during the performance phase. AI systems also yielded moderate improvements in learning outcomes and achievement ( g = 0.350, p = 0.034). Moderator analyses indicated stronger SRL effects among older learners, longer intervention durations, and language learning contexts employing interactive AI systems, while gender differences were minimal. Sensitivity and publication bias tests confirmed the stability of results.

Discussion

The findings indicate that AI functions as an adaptive scaffold that meaningfully enhances learners’ self-regulatory and self-directed capacities across cognitive, motivational, and reflective processes. By strengthening forethought and planning mechanisms in particular, AI-based interventions support more autonomous, sustained, and effective learning behaviors that translate into measurable academic benefits. Variability in behavioral regulation outcomes highlights the need for more explicit action-level supports in AI design. Overall, the results showcase AI’s potential to promote equitable and scalable self-regulated learning across diverse educational contexts, while also pointing to the importance of aligning intervention design with learner characteristics and instructional goals.

Zitieren

APA

Achuthan, K. (2025). Artificial intelligence and learner autonomy: a meta-analysis of self-regulated and self-directed learning. Frontiers in Education, 10. https://doi.org/10.3389/feduc.2025.1738751

Vancouver

Achuthan K. Artificial intelligence and learner autonomy: a meta-analysis of self-regulated and self-directed learning. Frontiers in Education. 2025;10. doi:10.3389/feduc.2025.1738751

BibTeX
@article{Achuthan2025,
  author = {Achuthan, Krishnashree},
  title = {Artificial intelligence and learner autonomy: a meta-analysis of self-regulated and self-directed learning},
  journal = {Frontiers in Education},
  year = {2025},
  volume = {10},
  doi = {10.3389/feduc.2025.1738751}
}
Kostenlos starten →