Actionable companion · Feedback & scaffolding

Learning with agency: Effects of adaptive feedback through a digital tool – a mixed-methods study on the course of self-regulated learning

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.

Read original paper Search paper agent CC BY 4.0

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): Higher education, Adult & professional learning. Verify the participant population and task before transferring the findings.

Original authors’ abstract, reproduced under the linked source license:

Abstract Lifelong learning is emerging as a key priority for promoting equity and sustainability in societies. Self-regulated learning (SRL) is a fundamental requirement for achieving successful lifelong learning, and digitization is increasingly influential in this regard. This mixed-methods study explores the degree to which adaptive learning technology (ALT) can assist university students in their SRL with timely and personalized support. Additionally, the study examines how students perceive this feedback and incorporate it into their learning behavior. Using hierarchical linear modeling, we investigated the development of SRL over a 9-week period. Semi-structured interviews were conducted with purposively selected learners, based on stimulated recalls. The quantitative results demonstrate positive development in certain components of SRL. Furthermore, the results indicate that metacognitive activity can be partially predicted by motivational and emotional states. The qualitative findings reveal that learners have varying perceptions of feedback received from ALT and integrate it into their learning behaviors based on their individual benefits. The results support the assumption that feedback provided through educational technology must be precisely tailored to the needs of learners, taking into account the dynamics of their individual learning processes. The study contributes to the ongoing discussion on the design of educational technology. Supplementary Information The online version contains supplementary material available at 10.1007/s10639-024-12510-8. Keywords: Self-regulated learning, Adaptive learning technology, Feedback, Mixed-methods

What kind of evidence is this?

Intelligent tutoring & adaptive learning · Qualitative / mixed methods

Stage: Higher education; Adult & professional learning. 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 present study used a mixed-methods design, specifically a convergent parallel research design (Creswell and Plano-Clark, 2018), to combine qualitative and quantitative strands of research (Fig. 3). This approach allowed us to address the need for more qualitative studies in SRL research (Pekrun, 2020), and provided both broad and deep insights into the development and promotion of SRL through a digital tool (Anthonysamy et al., 2020; Kelle, 2015; McCardle & Hadwin, 2015).

Limitations and uncertainty · source passage

An important theoretical implication from our study is the suitability of the prefabricated learning strategies presented to learners through video in our digital tool. It is possible that these strategies may not adequately fit the specific learning needs of individual learners. This issue is consistent with the idea presented by Pammer-Schindler and colleagues (Pammer-Schindler et al., 2018) that digital platforms may not be tailored enough to students’ individual needs and abilities, leading to lower usage. In future, it would be of interest to develop adaptive and personalized approaches that incorporate and process learners’ needs even more effectively (Park et al., 2022), by for example combining ALTs with natural language processing (Mejeh & Rehm, in press). Methodologically, multilevel models are a valid approach for capturing individual learning trajectories. In this regard, it could be highly advantageous in the future to more closely examine single intra-individual developments and model them with greater specificity. Accordingly, linking nomothetic and ideographic analyses more intensively (Schmitz, 2000), potentially within the context of learning analytics data (Winne, 2017), could significantly enhance the further development of the SRL field. Practical implications arise from our study in that questions of designing SRL-conducive learning environments should be addressed more strongly in the future. Especially in flipped classroom settings in higher education, student engagement and active learning could be addressed, e.g., through appropriate assignments or group work (Kapur et al., 2022). In addition, it is crucial to prioritize the needs of both learners and instructors when designing ALTs. This can be accomplished through participatory research approaches that actively involve users in the development of educational technology. In our study, managing the triad of research, users, and IT development proved challenging, necessitating constant translation processes between the different levels. To guard against undesirable outcomes or failures, it is advisable to conduct multiple pilot tests and validation loops with the ALTs before the actual study.

Design the system before the pilot

Document the learner model, mastery rule, hint sequence and adaptation signal. Compare adaptive routing with the same content in a non-adaptive sequence. Check whether early errors lead to persistent low-expectation pathways.

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.
Measure engagement separately from achievement. Check whether novelty-driven participation persists and whether it translates to independent performance.

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. Choose one disciplinary task. Require a first attempt, a documented AI consultation, a critique of the output and an independent explanation. Align the comparison group and scoring rubric with the same objective. 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. Blind-score reasoning and accuracy on a new task without AI. Distinguish model examination scores, student perceptions and actual learner gains; only the last directly tests educational benefit. 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

Mathias Mejeh; Livia Sarbach; Tina Hascher. Effects of adaptive feedback through a digital tool – a mixed-methods study on the course of self-regulated learning. Education and Information Technologies (2024-03-02). https://doi.org/10.1007/s10639-024-12510-8

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.