← All research

AI for Learning

This paper reveals that how quickly students start online learning sessions (their "delayed start behavior") can predict their academic performance in both math and English.

cs.CYSome background helpsTracked lab · Human-Computer Interaction Institute

Cross-Subject Predictive Validity for Learning Outcomes of Delayed Start Behavior

Jordan Gutterman, Ashish Gurung, Lee Branstetter, Kenneth Koedinger +1 more

In plain terms

This research tackles the challenge of understanding student motivation and self-regulation using their digital learning behaviors. The authors investigated "delayed start behavior," which measures the time a student waits before beginning an online learning session. They analyzed data from 711 seventh-grade students using the iReady platform, examining if these delays predicted performance on standardized tests. They found that students who frequently delayed starting their math practice sessions tended to perform worse on both math and English standardized tests. Conversely, they identified "early starters" (20% of students) who showed greater academic growth, while "chronic delayers" (another 20%) experienced the opposite trend. This suggests that simply observing start times can provide valuable insights into student engagement and learning outcomes.

Why it matters · This research introduces an easily observable behavioral metric that can help educators identify students who might need support, offering a new, content-independent way to monitor student engagement and self-regulation in digital learning environments.

About this work · This study contributes to the field of learning analytics, focusing on using behavioral data to understand and predict student outcomes. Notably, authors Kenneth Koedinger and Vincent Aleven are affiliated with Carnegie Mellon University's HCII & LearnLab, a leading research group in human-computer interaction and AI in education.

Learning AnalyticsStudent ModelingBehavioral DataSelf-RegulationEngagement