In-vivo Experimentation Steve Ritter Founder and Chief Scientist Carnegie Learning ©2012 Carnegie Learning, Inc. An attempt to find meaning in three acts • Design: Geometry Contiguity (Vincent Aleven, Kirsten Butcher) • Modeling: Adjusting learning curve parameters (Cen, Koedinger, Junker) • Personalization: Word problem content (Candace Walkington) ©2012 Carnegie Learning, Inc. DESIGN ©2012 Carnegie Learning, Inc. Geometry angles ©2012 Carnegie Learning, Inc. Contiguity Early Version Research Version Commercial Version (Carnegie Mellon) (Carnegie Learning) Butcher, K., & Aleven, V. (2008). Diagram interaction during intelligent tutoring in geometry: Support for knowledge retention and deep transfer. In C. Schunn (Ed.) Proceedings of the Annual Meeting of the Cognitive Science Society, CogSci 2008. New York, NY: Lawrence Earlbaum. Hausmann, R.G.M. & Vuong, A. (2012) Testing the Split Attention Effect on Learning in a Natural Educational Setting Using an Intelligent Tutoring System for Geometry. In N. Miyake, D. Peebles, & R. P. Cooper (Eds.), Proceedings of the 34th Annual Conference of the Cognitive Science Society. (pp. 438-443). Austin, TX: Cognitive Science Society. ©2012 Carnegie Learning, Inc. Early Tutor ©2012 Carnegie Learning, Inc. Revised (commercial) tutor ©2012 Carnegie Learning, Inc. Geometry Contiguity • Design and field experimentation – Butcher and Aleven (2008) • Diagram interaction led to better transfer and retention • Analysis of impact – Hausmann and Vuong (2012) • Unit-level effects mixed • Advantage for harder skills ©2012 Carnegie Learning, Inc. Geometry Angles ©2012 Carnegie Learning, Inc. Lessons • Change is constant • Transition from research to production always requires adaptation ©2012 Carnegie Learning, Inc. MODELING ©2012 Carnegie Learning, Inc. Skillometer ©2012 Carnegie Learning, Inc. Expression Writing ©2012 Carnegie Learning, Inc. What gets learned? ©2012 Carnegie Learning, Inc. Bayesian Knowledge Tracing Cognitive tutor traces these skills differently ©2012 Carnegie Learning, Inc. Learning Curve Parameter Fitting • Field study looking at learning area of geometric figures – One group used adjusted learning parameters based on previous year’s data • Optimized group took 12% less time to reach same performance • • Significant learning gain in both groups No difference in learning gain between groups (p = 0.772 ) 120 100 80 Optimized 60 Control 40 20 le irc C Po ly go n Tr ap ez oi d Tr ia ng le Sq ua re Pa ra l le lo gr am 0 16©2012 Carnegie Learning, Inc. Lessons • Learning efficiency is a great outcome • Small, systemic changes can have big impact • Optimizing skills requires appropriate skill model – Koedinger, McLaughlin and Stamper (2012) LFA ©2012 Carnegie Learning, Inc. PERSONALIZATION ©2012 Carnegie Learning, Inc. Word problem customization ©2012 Carnegie Learning, Inc. Personalization field study • Students who got problems related to their interests made fewer errors • Also affected subsequent unit • Interaction with readability ©2012 Carnegie Learning, Inc. Lessons • Content matters – Challenge for knowledge component modeling • Are we personalizing preferences, reading level or both? ©2012 Carnegie Learning, Inc. Summary • It’s not about whether A is better than B – It’s about why A is better than B ©2012 Carnegie Learning, Inc.