In-vivo Experimentation

22
©2012 Carnegie Learning, Inc. In-vivo Experimentation Steve Ritter Founder and Chief Scientist Carnegie Learning

description

In-vivo Experimentation. Steve Ritter Founder and Chief Scientist Carnegie Learning. An attempt to find meaning in three acts. Design : Geometry Contiguity (Vincent Aleven , Kirsten Butcher) Modeling : Adjusting learning curve parameters (Cen, Koedinger , Junker) - PowerPoint PPT Presentation

Transcript of In-vivo Experimentation

Page 1: In-vivo Experimentation

©2012 Carnegie Learning, Inc.

In-vivo Experimentation

Steve RitterFounder and Chief Scientist

Carnegie Learning

Page 2: In-vivo Experimentation

©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)

Page 3: In-vivo Experimentation

©2012 Carnegie Learning, Inc.

DESIGN

Page 4: In-vivo Experimentation

©2012 Carnegie Learning, Inc.

Geometry angles

Page 5: In-vivo Experimentation

©2012 Carnegie Learning, Inc.

ContiguityEarly Version Commercial Version

(Carnegie Learning)

Research Version

(Carnegie Mellon)

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.

Page 6: In-vivo Experimentation

©2012 Carnegie Learning, Inc.

Early Tutor

Page 7: In-vivo Experimentation

©2012 Carnegie Learning, Inc.

Revised (commercial) tutor

Page 8: In-vivo Experimentation

©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

Page 9: In-vivo Experimentation

©2012 Carnegie Learning, Inc.

Geometry Angles

Page 10: In-vivo Experimentation

©2012 Carnegie Learning, Inc.

Lessons• Change is constant• Transition from research to

production always requires adaptation

Page 11: In-vivo Experimentation

©2012 Carnegie Learning, Inc.

MODELING

Page 12: In-vivo Experimentation

©2012 Carnegie Learning, Inc.

Skillometer

Page 13: In-vivo Experimentation

©2012 Carnegie Learning, Inc.

Expression Writing

Page 14: In-vivo Experimentation

©2012 Carnegie Learning, Inc.

What gets learned?

Page 15: In-vivo Experimentation

©2012 Carnegie Learning, Inc.

Bayesian Knowledge Tracing

Cognitive tutor traces these skills differently

Page 16: In-vivo Experimentation

©2012 Carnegie Learning, Inc.16

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 )

0

20

40

60

80

100

120

Square

Parallelogram

Triangle

Trapezoid

Polygon

Circle

Optimized

Control

Page 17: In-vivo Experimentation

©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

Page 18: In-vivo Experimentation

©2012 Carnegie Learning, Inc.

PERSONALIZATION

Page 19: In-vivo Experimentation

©2012 Carnegie Learning, Inc.

Word problem customization

Page 20: In-vivo Experimentation

©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

Page 21: In-vivo Experimentation

©2012 Carnegie Learning, Inc.

Lessons• Content matters– Challenge for knowledge component

modeling• Are we personalizing preferences,

reading level or both?

Page 22: In-vivo Experimentation

©2012 Carnegie Learning, Inc.

Summary• It’s not about whether A is better

than B– It’s about why A is better than B