Click here for the AutoMentor website
This project will develop a system for producing automated professional mentoring (called AutoMentor) as critical piece of technological infrastructure for a new, more motivating, and more inclusive approach to STEM education. Students are motivated to learn STEM concepts because they play computer games based on STEM professions. The project will add two important components to prior work on NSF-funded STEM computer games, such as Urban Science. First, we will develop automated mentoring technology with AutoMentor, building on previous research on automated tutoring systems (specifically on AutoTutor, a computer tutor that helps students learn about science and technology topics by holding a conversation in natural language with the learner). Second, we will implement Evidence Centered Assessment Design and Epistemic Network Analysis, a methodology developed with NSF funding to assess students’ ability to think and act like STEM professionals through game play. The project will use a Wizard of Oz methodology, in which data will be collected about player/mentor interactions over multiple instances of game play, whereas the resulting database will be used to develop and validate a system for automatically coding interactions. The coded database will then be used to generate automated responses to player actions in the game through AutoMentor. The resulting system will be tested to see whether players’ STEM learning with automated mentoring are comparable to outcomes with live mentors. This project is a collaboration between University of Wisconsin, University of Memphis, University of Maryland, and Massachusetts Audubon Society.
PI: David Shaffer (University of Wisconsin-Madison)
Co-PIs: Michael Gleicher, Art Graesser, Robert Mislevy, Kristen Scopinich
Grant Name: AutoMentor: Virtual mentoring and assessment in computer games for STEM learning
Grant Number: 0918409
Funding Agency: NSF (subcontract from University of Wisconsin; David Shaffer is PI)