The team is creating a hybrid human-AI tutoring system that gives each student the necessary amount of tutoring based on their individual needs. The project builds on decades of learning science research through cutting-edge tutor training and an AI-powered app that gives tutors ‘superhuman’ power, allowing them to reach all students rapidly and effectively. Using the app, tutors can access data from students’ existing math software to use motivational support tools and personalize learning in real-time.
CMU

Project Title

PLUS - Personalized Learning Squared: Doubling Math Learning by Optimizing Tutoring from Training to Practice

   Pennsylvania, Maryland, and California

Where it is used:

  • Central Unified School District in Fresno, California
  • Pittsburgh Public Schools in Pittsburgh, Pennsylvania
  • School District of Lancaster in Lancaster, Pennsylvania
  • Life Male Steam Academy in Pittsburgh, Pennsylvania
  • Gateway School District in Monroeville, Pennsylvania
  • Prince George’s County School District in Maryland
Project Summary
 

What’s the problem that Carnegie Mellon University is trying to solve?

High-impact tutoring is a proven solution to address math learning loss, however, millions of middle students don’t have access to personalized math tutoring.

What does PLUS do?

PLUS makes high tutoring for low-income students accessible at scale by combining human and AI tutors. The PLUS system analyzes students’ data as they work in school, and based on their individual math and motivational needs, assigns a human tutor or math practice software to them.

What is the wow factor?

PLUS Tutors use PLUS Training, research-backed tutor lessons based on the SMART framework that is available for free to all, and the PLUS Toolkit system which uses AI to identify student needs and suggest intervention strategies. 

How does it work?

The PLUS system optimally allocated learning resources to students. Students who are successfully using the math software continue to practice problems using it, while students who need motivational or emotional support work with a human tutor while gradually moving toward self regulated learning. 

Learn More
or contact Shivang Gupta at shivang@cmu.edu

Team Members

Ken Koedinger
Professor of Human Computer Interaction and Psychology at Carnegie Mellon University
Shivang Gupta
Head of Product at Carnegie Mellon University
Emma Brunskill
Associate Professor in the Computer Science Department at Stanford University
Danielle Thomas
Systems Scientist in the Human-Computer Interaction Institute within the School of Computer Science at Carnegie Mellon University
Lee Branstetter
Professor of Economics and Public Policy at Carnegie Mellon University
Vincent Aleven
Professor of Human-Computer Interaction & Director, Creating Adaptive Tutoring Systems (CATS) Lab