Empirical research on the Pepper robot in formal education is recent, concentrated in primary education, and dominated by qualitative designs with small samples¶

Claim · All claims
Evidence · 1 study · review r2 · q2
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? Of 13 included empirical studies, eight (61.5%) used qualitative approaches and eight (61.5%) had samples of fewer than 50 participants, with no large-scale longitudinal studies identified. → Martinez-Roig 2026

Evidence¶

Martinez-Roig 2026¶

Martinez-Roig, R., Aragonés-González, M., & Cazorla, M. (2026). Exploring the implementation of the Pepper social robot in formal education: a scoping review. Journal of New Approaches in Educational Research, 15, 22. https://doi.org/10.1007/s44322-026-00072-1

q2 · i? · review · r2

Scoping review synthesis of 13 peer-reviewed empirical studies on Pepper in formal education, selected via PRISMA-ScR from four databases (2014–2026). The review reports the methodological distribution verbatim: "eight studies (61.5%) adopted qualitative approaches" and "No large-scale longitudinal studies were identified."

"From a methodological perspective, eight studies (61.5%) adopted qualitative approaches, including case studies or interaction analysis. Three studies (23.1%) used mixed-methods designs and two (15.4%) employed predominantly quantitative experimental designs. No large-scale longitudinal studies were identified."

Discussion¶

Related Claims¶

• Research settings split between formal educational environments (16 studies) and informal learning contexts (eight studies) — related
• Reported benefits of Pepper centre on motivation and engagement, with social-skill and academic-performance gains reported less frequently — related
• Pepper has been deployed in three predominant pedagogical roles: tutor/teaching assistant, learning partner or tutored agent, and social mediator in inclusive settings — related
• Technical difficulties were the most frequently reported implementation limitation, mentioned in ten of the thirteen studies — related
• In second-language teaching for pupils with special educational needs, Pepper was associated with higher participation than digital tablets — related
• Pepper's classroom operation required frequent teacher supervision in over half of the studies, mainly due to voice recognition and technical failures — related
• Recognition of individual Pepper-produced LIS signs varies widely, with several signs significantly above chance and others not significant — related
• STEAM AI literacy studies rely mainly on mixed (41.0%) and qualitative (35.9%) methods, with large-scale quantitative work limited (23.1%) — reports the opposite
• Empirical studies predominate in the corpus but mostly employ small or moderate samples (median 43.0 participants) — related
• Experimental, quasi-experimental, machine-learning, mixed-methods and survey designs dominate research assessing AI's impact on engagement and satisfaction — related
• Special issue findings are soft: small-scale case studies limit generalizability — related
• Research on AI support for EL literacy remains limited, narrow in scope, and lacking for diverse EL subgroups — a broader claim this one bears on
• Robot-assisted language learning is a rapidly developing field with increasing implementation of robots as language tutors — related
• The evidence base is dominated by US studies and quantitative designs, with sample sizes ranging from one teacher to 53 schools and 1,323 teachers — related