Predicting Student Self-regulation Strategies in Game-Based Learning Environments

Abstract

Self-regulated learning behaviors such as goal setting and monitoring have been found to be key to students’ success in a broad range of online learning environments. Consequently, understanding students’ self-regulated learning behavior has been the subject of increasing interest in the intelligent tutoring systems community. Unfortunately, monitoring these behaviors in real-time has proven challenging. This paper presents an initial investigation of self-regulated learning in a game-based learning environment. Evidence of goal setting and monitoring behaviors is examined through students’ text-based responses to update their ‘status’ in an in-game social network. Students are then classified into SRL-use categories that can later be predicted using machine learning techniques. This paper describes the methodology used to classify students and discusses initial analyses demonstrating the different learning and gameplay behaviors across students in different SRL-use categories. Finally, machine learning models capable of predicting these categories early into the student’s interaction are presented. These models can be leveraged in future systems to provide adaptive scaffolding of self-regulation behaviors.