Actionable companion · Feedback & scaffolding

Learning with agency: Unravelling dynamic trajectories of epistemic emotions in a technology‐enhanced problem‐solving task: A multimodal data approach

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. Verify the participant population and task before transferring the findings.

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

Abstract Background Scholars have reached a consensus on the influential roles and dynamic characteristics of epistemic emotions during the problem‐solving process; however, few research provided empirical evidence to reveal the temporal progression of these emotions. Aims This study leverages multimodal data—self‐reports and physiological sensors—to examine variations in a focal epistemic emotion across learning phases and performance levels and to uncover transition patterns among different epistemic emotions. Samples A total of 105 students enrolled in a five‐year undergraduate medical program were involved in the data analysis. Methods Participants diagnosed a virtual patient in an intelligent tutoring system designed based on the self‐regulated learning (SRL) model. We recorded electrodermal activity (EDA) peaks as an indicator of physiological arousal and collected self‐reports of surprise, curiosity, confusion, enjoyment and boredom across three SRL phases. Two‐way mixed‐design ANOVAs examined variations in the focal emotion and EDA peaks across the forethought, performance and self‐reflection phases, comparing high‐ and low‐performing groups. Temporal network analysis was used to identify transition patterns between emotions during the self‐regulated problem‐solving process. Results Epistemic emotions varied distinctly by performance level and SRL phase. For instance, high performers' confusion decreased over time, while low performers showed persistently high confusion. EDA peaks were more frequent during forethought and self‐reflection phases for both groups. More importantly, temporal network analysis revealed several key emotional transitions, including surprise/curiosity → confusion and enjoyment → surprise/boredom. Conclusions Overall, this study offers empirical insights into the temporal trajectories of epistemic emotions, informing targeted emotional scaffolding across learning phases. Keywords: emotional trajectories, epistemic emotions, multimodal data

What kind of evidence is this?

Intelligent tutoring & adaptive learning · Design requires full-text appraisal

Stage: Higher education. 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

A total of 112 medical students from a large research‐intensive university in the northeastern Chinese Mainland volunteered to participate in this study. All participants were in the fourth year of a five‐year undergraduate medical program. Since this study employed the physiological signal to indicate emotional arousals, seven participants were excluded due to low‐quality signal, leading to a sample of 105 students included in the final data analysis. The sample consisted of 63 female and 42 male students, with an average age of 22.70, SD = 2.54. Prior to data collection, we had obtained the approval of a Research Ethics Board. Moreover, participants had completed several prerequisite courses, such as endocrinology, metabolism and pathology, ensuring that they mastered the prior knowledge required for solving the diagnostic problem‐solving tasks involved in this study.

Limitations and uncertainty · source passage

Despite these remarkable findings, this study is not without limitations. First, participants reported their perceived epistemic emotions at only three time points to minimize interruptions to their cognitive processes. Future research could benefit from employing think‐aloud protocols and facial expression analyses, which allow for the observation of learners' fine‐grained emotional responses. Second, due to the relatively small sample size, this study did not compare the temporal networks of epistemic emotions between high‐ and low‐performing students to maintain an acceptable model fit. Future investigations should consider examining these differences, as exploring emotional transitions across performance levels may yield valuable insights. As well, individual factors, such as trait emotions and prior knowledge, matter in interpreting diverse emotional trajectories, requiring the incorporation of these factors into future research. Third, this study was conducted in the context of a diagnostic problem‐solving task within an intelligent tutoring system. Given that different technologies may affect learners' cognitive and affective processes in distinct ways, future research can explore the dynamics of epistemic emotions in interactions with generative artificial intelligence tools. Another notable limitation of the current study is the use of a virtual learning environment BioWorld. While the simulated virtual patients enable a safe training environment for medical students, the low‐stakes nature may lead to diminished emotional involvement compared to real‐world clinical settings. In actual practice, the ethical and professional responsibility for a patient's health likely amplifies the intensity of epistemic emotions like confusion. Future research should be conducted in high‐ecology situations to reveal the emotional trajectories in authentic problem‐solving tasks.

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.
Use common rubrics, blind scoring where feasible and a fresh unaided reasoning task. Document permissible assistance and avoid treating AI-detector scores as proof of misconduct.

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

Tingting Wang; Jianhua Zhang; Shasha Li; Jie Gao; Lingyun Huang; Susanne P Lajoie. Unravelling dynamic trajectories of epistemic emotions in a technology‐enhanced problem‐solving task: A multimodal data approach. The British Journal of Educational Psychology (2026-03-16). https://doi.org/10.1111/bjep.70073

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.