An automated agent responding to detected gaming-the-system reduced gaming by half and improved gaming students' learning¶

Claim · All claims
Evidence · 1 study · review r2 · q2
Currency · newest study 2012 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? In a USA classroom study, an agent that gave supplementary exercises and displayed displeasure when students gamed reduced gaming by half and improved gaming students' learning relative to control. → Kenneth R. Koedinger 2012

Evidence¶

Kenneth R. Koedinger 2012¶

Kenneth R. Koedinger, Emma Brunskill, Ryan S.J.d. Baker, Elizabeth A. McLaughlin, and John Stamper. (2012). New Potentials for Data-Driven Intelligent Tutoring System Development and Optimization. http://learnlab.org/datashop

q2 · i? · review · r2

Classroom study of an automated intervention built on a gaming-the-system detector (Baker et al. 2006, as reported in this article). The article reports the agent "reduced gaming by half and improved gaming students’ learning relative to the control condition".

"This agent gave students supplementary exercises on material bypassed through gaming, and displayed displeasure when the student games. In a classroom study in the USA, this agent reduced gaming by half and improved gaming students’ learning relative to the control condition"

Discussion¶

Related Claims¶

• Scooter the Tutor was associated with a marginally significant reduction in observed gaming among middle-school math students — related
• Students receiving the most Scooter supplementary exercises showed significantly better learning and caught up by post-test, though there was no overall between-condition learning effect — related
• Automated detectors of disengaged behaviors inferred from interaction-log data alone reached AUC over 0.8 for gaming and correlated 0.55 with observed off-task behavior — related