Parenting Journal · Volume 3 · Issue 1 · Licensed source edition
Affective Computing Approaches in Child–Robot Interaction: A Systematic Review and Taxonomy
Originally published 2026-09-09 · Sensors (Basel, Switzerland)
Multidisciplinary Digital Publishing Institute (MDPI) · DOI 10.3390/s26185721 ↗
AI / system type
Mixed affective computing/social robots; machine learning, scripted/hybrid control, 14 Wizard-of-Oz and three LLM/GenAI studies
Child-facing evidenceExamines children or child-focused systems. Transfer to everyday family life must be assessed separately.
The AI connection
Mixed affective computing/social robots; machine learning, scripted/hybrid control, 14 Wizard-of-Oz and three LLM/GenAI studies. Examines how child emotion signals are sensed, interpreted and connected to robot responses.
Why this reading matters
A broad critical synthesis explicitly separating emotion detection from appropriate supportive action and highlighting data-governance gaps.
Editorial reading guide · Kindness
What does an emotionally intelligent child-facing robot actually understand?
Examines how child emotion signals are sensed, interpreted and connected to robot responses.
Study context
105 child–robot affective-computing studies
Age / stage: Child-focused studies; ages vary across included research
Read with three questions
- How often were adult-trained models used for children?
- Was emotion prediction linked to meaningful adaptation?
- What privacy and ecological-validation gaps were identified?
Keep the limits in view
Heterogeneous small and short studies; no pooled clinical-effectiveness estimate. Limited child-specific datasets and real-world validation; very few LLM studies. Affective labels are not proof of internal experience.
The text below is the original article’s licensed repository edition. Its wording is not rewritten. Use the Paper Agent beside the text to locate evidence; open the source for figures, tables and complete context.
Opening the verified paper and agent…
Checking the article identity, license record, and saved source text.
Open the repository recordAttribution & reuse
Follow the original.
Original authorship, publication date, journal and DOI are preserved. This issue’s TRICK placement and reading questions are editorial additions, not claims made by the original authors.
Sandra Cano; Juan Pablo Vásconez; Kiara Villarroel; Juan Carlos Geraldo; Sergio Albiol-Pérez (2026). Affective Computing Approaches in Child–Robot Interaction: A Systematic Review and Taxonomy Sensors (Basel, Switzerland). https://doi.org/10.3390/s26185721
Permissions checked against the saved article notice; repository publication notices screened 2026-11-04. This is not a new peer-review decision. The source authors and publishers are not represented as endorsing this issue.