Search
Program Calendar
Browse By Day
Browse By Time
Browse By Person
Browse By Room
Browse By Unit
Browse By Session Type
Search Tips
Annual Meeting Registraion, Housing and Travel
Personal Schedule
Sign In
This study investigates how we can effectively predict students struggling (through hurdles) within a game-based environment for learning. Our sample of 1,469 students from K-5th grade interacted with a game-based environment for math learning, ST Math, in the Fall and Winter of SY 2017-2018. Predictive models that include math achievement score before gameplay (pre-test) and a variety of game actions (learning objectives covered, number of game levels attempted, game level score, puzzles passed on first attempt, etc.) are analyzed. Using decision tree analyses, the results indicate that behavior within game-based environments are not necessarily driven solely by their math content knowledge. Instead a more holistic view of the learning experience is needed to inform behavioral patterns within digital learning systems.