TY - JOUR

T1 - A Step-Based Tutoring System to Teach Underachieving Students How to Construct Algebraic Models

AU - VanLehn, Kurt

AU - Milner, Fabio

AU - Banerjee, Chandrani

AU - Wetzel, Jon

N1 - Funding Information:
This research was supported by NSF 1628782, NSF 1840051 and The Diane and Gary Tooker Chair for Effective Education in Science, Technology, Engineering and Math.
Publisher Copyright:
© 2023, International Artificial Intelligence in Education Society.

PY - 2023

Y1 - 2023

N2 - An algebraic model uses a set of algebraic equations to describe a situation. Constructing such models is a fundamental skill, but many students still lack the skill, even after taking several algebra courses in high school and college. For such students, we developed instruction that taught students to decompose the to-be-modelled situation into schema applications, where a schema represents a simple relationship such as distance-rate-time or part-whole. However, when a model consists of multiple schema applications, it needs some connection among them, usually represented by letting the same variable appear in the slots of two or more schemas. Students in our studies seemed to have more trouble identifying connections among schema applications than identifying the schema applications themselves. We developed several tutoring systems and evaluated them in university classes. One of them, a step-based tutoring system called OMRaaT (One Mathematical Relationship at a Time), was both reliably superior (p = 0.02, d = 0.67) to baseline and markedly superior (p < 0.001, d = 0.84) to an answer-based tutoring system using only commercially available software (MATLAB Grader).

AB - An algebraic model uses a set of algebraic equations to describe a situation. Constructing such models is a fundamental skill, but many students still lack the skill, even after taking several algebra courses in high school and college. For such students, we developed instruction that taught students to decompose the to-be-modelled situation into schema applications, where a schema represents a simple relationship such as distance-rate-time or part-whole. However, when a model consists of multiple schema applications, it needs some connection among them, usually represented by letting the same variable appear in the slots of two or more schemas. Students in our studies seemed to have more trouble identifying connections among schema applications than identifying the schema applications themselves. We developed several tutoring systems and evaluated them in university classes. One of them, a step-based tutoring system called OMRaaT (One Mathematical Relationship at a Time), was both reliably superior (p = 0.02, d = 0.67) to baseline and markedly superior (p < 0.001, d = 0.84) to an answer-based tutoring system using only commercially available software (MATLAB Grader).

KW - Algebra story problem solving

KW - Algebra word problem solving

KW - Algebraic model construction

KW - Intelligent tutoring system

UR - http://www.scopus.com/inward/record.url?scp=85147110514&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85147110514&partnerID=8YFLogxK

U2 - 10.1007/s40593-023-00328-3

DO - 10.1007/s40593-023-00328-3

M3 - Article

AN - SCOPUS:85147110514

SN - 1560-4292

JO - International Journal of Artificial Intelligence in Education

JF - International Journal of Artificial Intelligence in Education

ER -