School entry detection of struggling readers using gameplay data and machine learning.

Introduction: Current methods for reading difficulty risk detection at school entry remain error-prone. We present a novel approach utilizing machine learning analysis of data from GraphoGame, a fun and pedagogical literacy app. Methods: The app was played in class daily for 10 min by 1,676 Norwegian first graders, over a 5-week period during the first months of schooling, generating rich process data. Models were trained on the process data combined with results from the end-of-year national screening test. Results: The best machine learning models correctly identified 75% of the students at risk for developing reading difficulties. Discussion: The present study is among the first to investigate the potential of predicting emerging learning difficulties using machine learning on game process data. [ABSTRACT FROM AUTHOR]