Agentic education · Learning science

Actionable companion · Assessment & reasoning

Learning with agency: Complex emotion recognition system using basic emotions via facial expression, electroencephalogram, and electrocardiogram signals: a review

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 paperSearch paper agentCC 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:

The Complex Emotion Recognition System (CERS) deciphers complex emotional states by examining combinations of basic emotions expressed, their interconnections, and their dynamic variations. Through the utilization of advanced algorithms, the system provides profound insights into emotional dynamics, facilitating a nuanced understanding and customized responses. Achieving this level of emotional recognition in machines necessitates knowledge distillation and the comprehension of novel concepts akin to human cognition. The development of artificial intelligence systems for discerning complex emotions poses substantial challenges with significant implications for affective computing. Also, obtaining a sizable dataset for such systems is daunting due to the intricacies involved in capturing subtle emotions, necessitating specialized methods for data collection and processing. Incorporating physiological signals, such as electrocardiograms (ECG) and electroencephalograms (EEG), notably enhances CERS by furnishing insights into users' emotional states, improving dataset quality, and fortifying system dependability. This study presents a comprehensive review assessing the efficacy of machine learning, deep learning, and meta-learning approaches in both basic and complex emotion recognition using facial expressions, EEG, and ECG signals. Selected research papers offer perspectives on potential applications, clinical implications, and results of such systems, intending to promote their acceptance and integration into clinical decision-making processes. Additionally, this study highlights research gaps and challenges in understanding emotion recognition systems, encouraging further investigation by relevant studies and organizations. Lastly, the significance of meta-learning approaches in improving system performance and guiding future research is underscored, with potential applications in universities for advancing educational research, monitoring student well-being, and developing intelligent tutoring systems.

What kind of evidence is this?

Intelligent tutoring & adaptive learning · Evidence synthesis

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

Consequently, generating compound micro-expression images presents numerous obstacles and limitations. The data in these datasets is captured using high-speed cameras that record slight facial movements at a high frame rate, typically ranging from 100 to 200 frames per second, enabling the detection of micro-expressions lasting between 1/25th and 1/5th of a second. Participants in these datasets engage in various tasks or are exposed to specific stimuli to evoke spontaneous emotional reactions, which are then documented (Yan et al., 2013, 2014; Davison et al., 2016; Zhao and Xu, 2019; Joloudari et al., 2024). The number of participants varies among the datasets.

Limitations and uncertainty · source passage

To address these limitations, meta-learning strategies have been developed to enhance adaptability and performance in emotion recognition systems. Meta-learning enables models to learn from fewer samples, adapt quickly to new tasks, and handle noisy labels, making it well-suited for complex emotion recognition (Wang K. et al., 2020). Techniques such as few-shot learning (Ding et al., 2019), continual learning (He et al., 2019), and reinforcement learning (Li and Xu, 2020) have demonstrated promising results. Given that most widely used datasets such as MultiPie, SFEW, RaFD, JAFFE, and FER2013 mainly focus on basic emotions, meta-learning offers a pathway to overcome data scarcity and improve recognition of complex emotional states (Mellouk and Handouzi, 2020; Wu et al., 2023).

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.

  • 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

  1. 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.
  2. 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.
  3. 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.
  4. 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

Javad Hassannataj Joloudari; Mohammad Maftoun; Bahareh Nakisa; Roohallah Alizadehsani; Meisam Yadollahzadeh-Tabari; Silvia Gaftandzhieva. Complex emotion recognition system using basic emotions via facial expression, electroencephalogram, and electrocardiogram signals: a review. Frontiers in Psychology (2026-03-02). https://doi.org/10.3389/fpsyg.2026.1682883

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.