Actionable companion · Feedback & scaffolding
Learning with agency: AI-driven gamification and metacognitive strategy development: a study of primary school English vocabulary learning from a self-regulated learning perspective
AI-assisted editorial implementation guide, separate from the original research. Proposed actions are not claims or recommendations attributed to the source authors. No independent peer review of this guide is asserted.
Evidence and context
Title and abstract screening; stage labels describe reported settings, not verified numerical ages. Design labels require full-text appraisal. Reported stage(s): Primary school. Verify the participant population and task before transferring the findings.
Original authors’ abstract, reproduced under the linked source license:
Abstract With the rapid advancement of artificial intelligence technology in education, AI-driven gamified learning environments offer innovative pathways for primary English vocabulary instruction. Grounded in self-regulated learning theory, this study systematically examines the mechanisms through which AI-personalised gamified environments influence metacognitive strategy development in primary pupils’ English vocabulary acquisition. Through a meta-analysis of 45 empirical studies conducted between 2019 and 2024, the research reveals that AI-driven gamified learning environments demonstrate significant effects in promoting vocabulary acquisition (Cohen’s d = 0.72), enhancing metacognitive awareness (Cohen’s d = 0.68), and improving learning persistence (Cohen’s d = 0.64). Adaptive feedback mechanisms played a crucial mediating role, effectively fostering learners’ self-regulation capabilities by dynamically adjusting learning pathways and delivering personalised guidance. The study further revealed the significant moderating effects of cultural context, technology acceptance, and teacher support on AI gamification outcomes. This research provides theoretical foundations and practical guidance for AI applications in language education, holding considerable value for advancing the design of personalised language learning environments. Keywords: adaptive feedback, artificial intelligence, gamified learning, metacognitive strategies, self-regulated learning, vocabulary acquisition
What kind of evidence is this?
Supporting AI learning science · Survey / observational study
Stage: Primary school. Screening labels describe reported context and study-design language. They are not a risk-of-bias rating or proof of effectiveness for an age band.
Study methods · source passage
The literature screening process was designed in accordance with the best practice standards outlined in the Cochrane Handbook for Systematic Reviews. A rigorous, multi-stage, multi-assessor procedure was implemented to ensure the objectivity and reliability of the screening process. The formulation of screening criteria fully considered the specificity of the research question and the methodological characteristics of AI gamified learning studies. Inclusion criteria required experimental or quasi-experimental designs at the study design level, a requirement grounded in the need for causal inference to ensure the included studies could provide credible evidence for evaluating the effectiveness of AI-gamified learning. Regarding intervention characteristics, studies were required to incorporate both AI technology and gamification elements. This criterion was established to ensure consistency in the research focus and prevent the inclusion of studies solely on AI technology or solely on gamification.
Limitations and uncertainty · source passage
Whilst yielding significant findings, this study also exhibits notable limitations that provide crucial directions for future research refinement. Firstly, although the geographical distribution of included studies exhibits some global representativeness, it remains predominantly concentrated in countries and regions with relatively advanced educational technology. Representation from developing nations and areas with relatively scarce educational resources remains limited. This distributional bias may impact the external validity of research conclusions, particularly in contexts exhibiting significant disparities in technology acceptance, infrastructure conditions, and teacher professional standards. Implementation in resource-constrained settings confronts compound structural barriers. Digital infrastructure deficits remain prohibitive: merely 34% of Sub-Saharan African and 47% of South Asian primary schools possess reliable connectivity adequate for real-time AI computation, whilst student-to-device ratios exceed 15:1 in 68% of low-income countries (UNESCO Institute for Statistics, 2023; World Bank, 2023). Teacher capacity gaps compound technological constraints—effective implementation requires dual competencies in system operation and AI-analytics interpretation, yet 73% of developing nations lack systematic AI literacy in pre-service curricula (UNESCO Institute for Statistics, 2023). Cultural-linguistic localisation deficits further undermine efficacy: gamification elements designed for individualist contexts demonstrate reduced engagement in collectivist settings (Tai et al., 2022), whilst NLP algorithms exhibit diminished accuracy for morphologically complex languages. Economic sustainability concerns remain underexamined—per-pupil annual costs ($120–$280) represent 15–35% of total educational expenditure in low-income contexts (Khasawneh, 2024), risking exacerbation rather than amelioration of global educational inequalities.
Design the system before the pilot
Use this study to inform a learning mechanism or implementation question. It is not direct evidence that autonomous agents improve learning. Keep the proposed agent behavior separate from what the source actually tested.
- Give feedback on the learner’s reasoning, then fade hints. Record whether the learner can complete the next task without that scaffold.
- Use plan–attempt–check–reflect prompts and compare confidence with actual performance. Keep learner choice and reflection visible.
A 90-day district pilot
- Days 1–15 · Appraise. Have the curriculum lead and a teacher read the methods and limitations. Record the study design, sample, comparator, outcomes and evidence gaps. Define a local question that the study can help inform.
- Days 16–30 · Design. Pilot one teacher-led unit with short guided turns. The tutor asks for an explanation and offers a graduated hint before any worked solution. Use concrete examples and an equivalent task without AI. Name an accountable owner and set the baseline, success threshold and budget before implementation.
- Days 31–60 · Test. Start with a small voluntary cohort, preserve an accessible non-AI route and require teacher review. Use synthetic or de-identified examples; approve data handling and tool terms through district processes.
- Days 61–90 · Decide. Use an age-appropriate independent post-task and a delayed parallel task. Score explanation quality and transfer, not the number of agent messages or completion rate alone. Compare with baseline, document uncertainty and stop or revise if learning worsens, access is unequal or critical errors persist.
The board decision brief
Report the learning problem, evidence quality, participating population, total cost including review time, measured benefit, errors, access differences and remaining uncertainties. Make a dated recommendation to stop, revise or expand. A positive perception survey alone does not establish learning improvement.
Attribution and reuse
Hongling Wu; Xingting Wang. AI-driven gamification and metacognitive strategy development: a study of primary school English vocabulary learning from a self-regulated learning perspective. Frontiers in Psychology (2026-03-09). https://doi.org/10.3389/fpsyg.2026.1692949
Companion prepared 2026-10-30. Original authorship and DOI are preserved. The abstract is an attributed source extract; the implementation plan is new AI-assisted editorial material, offered under the same CC BY 4.0 license. This guide has not undergone independent peer review.