Using Machine Learning to Detect SMART Model Cognitive Operations in Mathematical Problem-Solving Process

Self-regulated learning (SRL) is a critical component of mathematics problem-solving. Students skilled in
SRL are more likely to effectively set goals, search for information, and direct their attention and cognitive
process so that they align their efforts with their objectives. An influential framework for SRL, the SMART
model (Winne, 2017), proposes that five cognitive operations (i.e., searching, monitoring, assembling,
rehearsing, and translating) play a key role in SRL. However, these categories encompass a wide range of
behaviors, making measurement challenging – often involving observing individual students and recording
their think-aloud activities or asking students to complete labor-intensive tagging activities as they work. In
the current study, to achieve better scalability, we operationalized indicators of SMART operations and
developed automated detectors using machine learning. We analyzed students’ textual responses and
interaction data collected from a mathematical learning platform where students are asked to thoroughly
explain their solutions and are scaffolded in communicating their problem-solving process. Due to the rarity
in data for one of the seven SRL indicators operationalized, we built six models to reflect students’ use of
four SMART operations. These models are found to be reliable and generalizable, with AUC ROCs ranging
from .76-.89. When applied to the full test set, these detectors are relatively robust to algorithmic bias,
performing well across different student populations and with no consistent bias against a specific group of
students.