Chicago Robot Tutors Teach SEL Without Human Pretense

Factual robots outperform emotion-driven peers in study of social-emotional learning

Mar. 20, 2026 at 8:06am

Got story updates? Submit your updates here. ›

A research team from the University of Chicago has developed a new approach to using robots for social-emotional learning (SEL) in elementary classrooms. Unlike typical educational robots designed to mimic human emotions and personalities, these robots speak plainly without any fictional backstories or feelings. The study found that this straightforward, factual approach often led to deeper student engagement and better mastery of SEL concepts compared to both traditional classroom instruction and robots with fabricated personalities.

Why it matters

As concerns grow about children forming unhealthy attachments to AI, this research provides a model for using robots responsibly in education. By demonstrating that factual, non-emotive robots can be effective SEL tutors, the findings challenge assumptions about the need for robots to seem human-like in order to engage students. The results also highlight how robots can supplement teachers' capabilities without replacing the essential human element of teaching.

The details

The research, led by PhD student Lauren Wright and overseen by Assistant Professor Sarah Sebo at the University of Chicago, was conducted in partnership with Chicago Public Schools (CPS) and Chapin Hall. They observed SEL instruction in CPS classrooms, interviewed teachers, and then designed an experiment to test different robot approaches. In the study, 52 students were divided into three groups: one learned SEL from robots with fictional, emotion-laden dialogue, another worked with factual robots acknowledging they had no feelings, and a control group received regular classroom instruction. Both robot groups showed improved mastery of SEL concepts compared to the control, but the factual robots often encouraged deeper engagement with lesson vocabulary and problem-solving language.

  • The research was presented at the 2026 ACM/IEEE International Conference on Human-Robot Interaction (HRI) held in Edinburgh, Scotland in March 2026.
  • The classroom experiment took place during the 2025-2026 school year in Chicago.

The players

Lauren Wright

A PhD student at the University of Chicago's Department of Computer Science who led the research team.

Sarah Sebo

An Assistant Professor at the University of Chicago's Department of Computer Science who oversaw the research.

Chicago Public Schools (CPS)

The school district that provided access to classrooms and teachers for the research.

Kiljoong Kim

A researcher at Chapin Hall who helped build connections and partnerships that enabled the cross-institution project.

Second Step

The social-emotional learning curriculum used in the study, made possible through connections with Chapin Hall and Kiljoong Kim.

Got photos? Submit your photos here. ›

What they’re saying

“With this work, we wanted to create a team that would be able to uniquely design and study technology, informed by best practices in SEL education, with the input of principals, administrators, teachers, and students in Chicago Public Schools.”

— Sarah Sebo, Assistant Professor, University of Chicago Department of Computer Science

“Giving robots fictional personalities with the intent to make them more engaging is a common approach to educational robots, one which feels especially relevant for teaching SEL. However, in our research study, we found that the robot's fictional emotions and experiences may have distracted or made students feel less comfortable using lesson language. These findings challenge us to reconsider our assumptions when designing robot behaviors – just because an approach is common doesn't mean it will always lead to the best outcomes.”

— Lauren Wright, PhD Student, University of Chicago Department of Computer Science

“We firmly believe that human teachers are the most important element in elementary education. As we all experienced during the pandemic, replacing in-person educational experiences with technology-mediated ones can be disastrous. Our work does not seek to replace human teachers, but instead, aims to create robot tools that extend a teacher's reach, giving the ability to provide children with one-on-one attention without pulling them away from the rest of the class.”

— Sarah Sebo, Assistant Professor, University of Chicago Department of Computer Science

What’s next

The research team plans to continue studying how factual, non-emotive robots can be effectively integrated into elementary classrooms to supplement teachers' SEL instruction. They will also explore ways to scale the approach to more schools and districts.

The takeaway

This study challenges the conventional wisdom that educational robots need to mimic human emotions and personalities in order to engage students. By demonstrating the effectiveness of a straightforward, factual approach, the findings point the way to using robots responsibly in the classroom without the risks of unhealthy AI attachments. The research shows how technology can enhance teachers' capabilities without replacing the essential human element of teaching.