Actionable companion · Feedback & scaffolding
Learning with agency: The interaction effect of pedagogical agent and emotional feedback on effective learning: a 2 × 2 factorial experiment in online formative assessment
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): Age / stage not established. Verify the participant population and task before transferring the findings.
Original authors’ abstract, reproduced under the linked source license:
Introduction To address the challenge of face-to-face communication in online learning, integrating pedagogical agents and emotional feedback has been proposed as viable solutions. However, research on their impact during formative assessments remains limited. Methods This study therefore conducted a 2 (Pedagogical agent: present vs. absent) × 2 (Emotional feedback: present vs. absent) experimental study using an online learning system to explore their effects on learning performance. Results Results indicated that pedagogical agents had a slightly negative influence on transfer scores, while emotional feedback significantly boosted engagement. When both were combined, learners exhibited the highest motivation, although this did not significantly enhance emotional perception or performance and slightly reduced transfer scores. Notably, the use of these tools shortened learning duration. Discussion These findings suggest that educators should exercise caution when designing pedagogical agents in online formative assessment environments to avoid potential distractions during the learning process. Meanwhile, the integration of emotional feedback may contribute to creating a more humanized digital learning atmosphere, thereby supporting learners in their online learning experience. Overall, this study provides crucial insights into the complex effects of these tools on learning in computer-based online formative assessments, guiding future design and application.
What kind of evidence is this?
Conversational & pedagogical agents · Survey / observational study
Stage: Age / stage not established. 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
This study employs a 2 (Pedagogical agents: present vs. absent) × 2 (Emotional feedback: present vs. absent) between-subjects experimental design. The research variables are depicted in Figure 1.
Design the system before the pilot
Define whether the agent asks questions, gives hints, explains or assesses. Test hallucinated feedback, excessive praise, misleading confidence and responses when the learner is confused. A conversational interface alone does not establish autonomous agency.
- Give feedback on the learner’s reasoning, then fade hints. Record whether the learner can complete the next task without that scaffold.
- Include a delayed assessment and an unfamiliar transfer problem without AI. Immediate supported performance cannot establish durable learning.
- Measure engagement separately from achievement. Check whether novelty-driven participation persists and whether it translates to independent performance.
- 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. Treat the paper as background evidence until its population is verified in the full text. Do not assign an age-specific intervention or extend adult results to children. 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. Extract the participant ages or education stage, recruitment, task and comparator before selecting a local pilot. If these cannot be established, retain the paper for design discussion rather than age-band efficacy claims. 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
Xiaoqin Tang; Li Jiang; Guoli Liu; Hongxia Li. The interaction effect of pedagogical agent and emotional feedback on effective learning: a 2 × 2 factorial experiment in online formative assessment. Frontiers in Psychology (2025-07-28). https://doi.org/10.3389/fpsyg.2025.1610550
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.