Search

In recent years, an increasing number of analyses in Learning Analytics and Educational Data Mining (EDM) have adopted a "Discovery with Models" approach, where an existing model is used as a key component in a new EDM/analytics analysis. This article presents a theoretical discussion on the emergence of discovery with models, its potential to enhance research on learning and learners, and key lessons learned in how discovery with models can be conducted validly and effectively. We illustrate these issues through discussion of a case study where discovery with models was used to investigate a form of disengaged behavior, i.e., carelessness, in the context of middle school computer-based science inquiry. This behavior has been acknowledged as a problem in education as early as the 1920s. With the increasing use of high-stakes testing, the cost of student carelessness can be higher. For instance, within computer-based learning environments careless errors can result in reduced educational effectiveness, with students continuing to receive material they have already mastered. Despite the importance of this problem, it has received minimal research attention, in part due to difficulties in operationalizing carelessness as a construct. Building from theory on carelessness and a Bayesian framework for knowledge modeling, we use machine-learned detectors to predict carelessness within authentic use of a computer-based learning environment. We then use a discovery with models approach to link these validated carelessness measures to survey data, to study the correlations between the prevalence of carelessness and student goal orientation. [This paper was published in "American Behavioral Scientist" v57 n10 p1479-1498 2013.]

In recent years, the usefulness of affect detection for educational software has become clear. Accurate detection of student affect can support a wide range of interventions with the potential to improve student affect, increase engagement, and improve learning. In addition, accurate detection of student affect could play an essential role in research attempting to understand the root causes and impacts of different forms of affect. However, current approaches to affect detection have largely relied upon sensor systems, which are expensive and typically not physically robust to classroom conditions, reducing their potential real-world impact. Work towards sensor-free affect detection has produced detectors that are better than chance, but not substantially better--especially when subject to stringent cross-validation processes. In this paper we present models which can detect student engaged concentration, confusion, frustration, and boredom solely from students' interactions within a Cognitive Tutor for Algebra. These detectors are designed to operate solely on the information available through students' semantic actions within the interface, making these detectors applicable both for driving interventions and for labeling existing log files in the PSLC DataShop, facilitating future discovery with models analyses at scale. (Contains 1 figure and 2 tables.) [For the complete proceedings, "Proceedings of the International Conference on Educational Data Mining (EDM) (5th, Chania, Greece, June 19-21, 2012)," see ED537074.]