‒Assessing the Disengaged Behaviors of Learners

In recent years, an increasing number of models have been published that can infer if a learner is behaviorally disengaged while working within an interactive learning environment, and can conduct inference using features of data focused on learner interaction with the learning system. In this chapter, we discuss some of the behaviors that have been shown to be amenable to this type of modeling, including off-task behavior, gaming the system, and carelessness. We also consider some of the algorithms and approaches that have been found to be particularly effective. We contemplate the relative merits of knowledge engineering and data-mining approaches for this type of model, and focus on the key validity concerns that must be addressed for these types of models to be used with confidence in a comprehensive framework such as GIFT.