Comparing the prediction performance of item response theory and machine learning methods on item responses for educational assessments.

To obtain more accurate and robust feedback information from the students' assessment outcomes and to communicate it to students and optimize teaching and learning strategies, educational researchers and practitioners must critically reflect on whether the existing methods of data analytics are capable of retrieving the information provided in the database. This study compared and contrasted the prediction performance of an item response theory method, particularly the use of an explanatory item response model (EIRM), and six supervised machine learning (ML) methods for predicting students' item responses in educational assessments, considering student- and item-related background information. Each of seven prediction methods was evaluated through cross-validation approaches under three prediction scenarios: (a) unrealized responses of new students to existing items, (b) unrealized responses of existing students to new items, and (c) missing responses of existing students to existing items. The results of a simulation study and two real-life assessment data examples showed that employing student- and item-related background information in addition to the item response data substantially increases the prediction accuracy for new students or items. We also found that the EIRM is as competitive as the best performing ML methods in predicting the student performance outcomes for the educational assessment datasets.

Danger, high voltage! Using EEG and EOG measurements for cognitive overload detection in a simulated industrial context.

Industrial settings will be characterized by far-reaching production automation brought about by advancements in robotics and artificial intelligence. As a consequence, human assembly workers will need to adapt quickly to new and more complex assembly procedures, which are most likely to increase cognitive workload, or potentially induce overload. Measurement and optimization protocols need to be developed in order to be able to monitor workers' cognitive load. Previous studies have used electroencephalographic (EEG, measuring brain activity) and electrooculographic (EOG, measuring eye movements) signals, using basic computer-based static tasks and without creating an experience of overload. In this study, EEG and EOG data was collected of 46 participants performing an ecologically valid assembly task while inducing three levels of cognitive load (low, high and overload). The lower individual alpha frequency (IAF) was identified as a promising marker for discriminating between different levels of cognitive load and overload.

A Multidimensional IRT Approach for Dynamically Monitoring Ability Growth in Computerized Practice Environments.

Adaptive learning systems have received an increasing attention as they enable to provide personalized instructions tailored to the behaviors and needs of individual learners. In order to reach this goal, it is desired to have an assessment system, monitoring each learner's ability change in real time. The Elo Rating System (ERS), a popular scoring algorithm for paired competitions, has recently been considered as a fast and flexible method that can assess learning progress in online learning environments. However, it has been argued that a standard ERS may be problematic due to the multidimensional nature of the abilities embedded in learning materials. In order to handle this issue, we propose a system that incorporates a multidimensional item response theory model (MIRT) in the ERS. The basic idea is that instead of updating a single ability parameter from the Rasch model, our method allows a simultaneous update of multiple ability parameters based on a compensatory MIRT model, resulting in a multidimensional extension of the ERS ("M-ERS"). To evaluate the approach, three simulation studies were conducted. Results suggest that the ERS that incorrectly assumes unidimensionality has a seriously lower prediction accuracy compared to the M-ERS. Accounting for both speed and accuracy in M-ERS is shown to perform better than using accuracy data only. An application further illustrates the method using real-life data from a popular educational platform for exercising math skills.

An explanatory item response theory method for alleviating the cold-start problem in adaptive learning environments.

Electronic learning systems have received increasing attention because they are easily accessible to many students and are capable of personalizing the learning environment in response to students' learning needs. To that end, using fast and flexible algorithms that keep track of the students' ability change in real time is desirable. Recently, the Elo rating system (ERS) has been applied and studied in both research and practical settings (Brinkhuis & Maris, 2009; Klinkenberg, Straatemeier, & van der Maas in Computers & Education, 57, 1813-1824, 2011). However, such adaptive algorithms face the cold-start problem, defined as the problem that the system does not know a new student's ability level at the beginning of the learning stage. The cold-start problem may also occur when a student leaves the e-learning system for a while and returns (i.e., a between-session period). Because external effects could influence the student's ability level during the period, there is again much uncertainty about ability level. To address these practical concerns, in this study we propose alternative approaches to cold-start issues in the context of the e-learning environment. Particularly, we propose making the ERS more efficient by using an explanatory item response theory modeling to estimate students' ability levels on the basis of their background information and past trajectories of learning. A simulation study was conducted under various conditions, and the results showed that the proposed approach substantially reduces ability estimation errors. We illustrate the approach using real data from a popular learning platform.