Leveraging Student Goal Setting for Real-Time Plan Recognition in Game-Based Learning

Goal setting and planning are integral components of self-regulated learning. Many students struggle to set meaningful goals and build relevant plans. Adaptive learning environments show significant potential for scaffolding students' goal setting and planning processes. An important requirement for such scaffolding is the ability to perform student plan recognition, which involves recognizing students' goals and plans based upon the observations of their problemsolving actions. We introduce a novel plan recognition framework that leverages trace log data from student interactions within a game-based learning environment called CRYSTAL ISLAND, in which students use a drag-and-drop planning support tool that enables them to externalize their science problem-solving goals and plans prior to enacting them in the learning environment. We formalize student plan recognition in terms of two complementary tasks: (1) classifying students' selected problem-solving goals, and (2) classifying the sequences of actions that students indicate will achieve their goals. Utilizing trace log data from 144 middle school students' interactions with CRYSTAL ISLAND, we evaluate a range of machine learning models for student goal and plan recognition. All machine learning-based techniques outperform the majority baseline, with LSTMs outperforming other models for goal recognition and naive Bayes performing best for plan recognition. Results show the potential for automatically recognizing students' problem-solving goals and plans in game-based learning environments, which has implications for providing adaptive support for student self-regulated learning.