Predicting Off-task Behaviors for Adaptive Vocabulary Learning System

In many studies, engagement has been considered as an important aspect of effective learning. Retaining student engagement is thus an important goal in intelligent tutoring systems (ITS). My current studies with collaborators on Dynamic Support of Contextual Vocabulary Acquisition for Reading (DSCoVAR) include building prediction models for students’ off-task behaviors. By extracting linguistically meaningful features and historical context information from interaction log data, these studies illustrate how some types of off-task behavior can be modeled from behavioral logs. The results of this research contribute to existing studies by providing examples of how to extract behavioral measures and predict off-task behaviors within a vocabulary learning system. Identifying off-task behaviors can improve students’ learning by providing personalized learning materials: for example, off-task behavior classifiers can be used to achieve more accurate predictions of the student’s vocabulary mastery level, which in turn can improve the system’s adaptive performance. Toward our goal of developing highly effective personalized vocabulary learning systems, this research would benefit from expert feedback on issues that include: principled approaches for adaptive assessment and feedback in a vocabulary learning system; and alternative methods for defining and generating off-task labels.