We propose a novel model, Wide & Deep Item Response Theory (Wide & Deep IRT), to predict the correctness of students' responses to questions using historical clickstream data. This model combines the strengths of conventional Item Response Theory (IRT) models and Wide & Deep Learning for Recommender Systems. By leveraging clickstream…

Science, Technology, Engineering, and Mathematics student success is an important topic in higher education research. Recently, the use of data analytics in higher education administration has gain popularity. However, very few studies have examined how data analytics may influence Science, Technology, Engineering, and Mathematics student success.…

Online learning systems allow learners to freely access learning contents and record their interactions throughout their engagement with the content. By using data mining techniques on the student log data of those systems, it is possible to examine learning behavior and reveal navigation patterns through learning contents. This study was aimed at…

The increasing use of digital systems to support learning leads to a growth in data regarding both learning processes and related contexts. Learning Analytics offers critical insights from these data, through an innovative combination of tools and techniques. In this paper, we explore students' activities in a MOOC from the perspective of personal…

Academic achievement of a student in college always has a far-reaching impact on his further development. With the rise of the ubiquitous sensing technology, students' digital footprints in campus can be collected to gain insights into their daily behaviours and predict their academic achievements. In this paper, we propose a framework named…

Data collection and analysis is nothing new in computer-assisted language learning, but with the phenomenon of massive sets of human language collected into corpora, and especially integrated into systems driven by artificial intelligence, new opportunities have arisen for language teaching and learning. We are now seeing powerful artificial…

This paper addresses a key challenge in Educational Data Mining, namely to model student behavioral trajectories in order to provide a means for identifying students most at risk, with the goal of providing supportive interventions. While many forms of data including clickstream data or data from sensors have been used extensively in time series…

The widespread adoption of online courses opens opportunities for analysing learner behaviour and optimising web-based learning adapted to observed usage. Here, we introduce a mathematical framework for the analysis of time-series of online learner engagement, which allows the identification of clusters of learners with similar online temporal…

Using mobile technology and experience sampling in junior high school, real-time motivation and engagement were explored at four-levels: between lessons (up to 2 lessons per day; Level 1), between days (5 days per week; L2), between weeks (4 weeks; L3), and between students (113 students; L4). Findings for a 'random effects' model revealed…

Background: Historically, significant advances in scientific understanding have followed advances in measurement and observation. As the resolving power of an instrument increased, so have gains in the understanding of the phenomena being observed. Modern interactive systems are potentially the new "microscopes" when they are…

We introduce a novel approach to visualizing temporal clickstream behaviour in the context of a degree-satisfying online course, "Habitable Worlds," offered through Arizona State University. The current practice for visualizing behaviour within a digital learning environment is to generate plots based on hand-engineered or coded features…

In e-learning systems, tutors have a significant impact on learners' life to increase their knowledge level and to make the learning process more effective. They are characterized by different features. Therefore, identifying tutoring styles is a critical step in understanding the preference of tutors on how to organize and help the learners. In…

Our learning-by-teaching environment, Betty's Brain, captures a wealth of data on students' learning interactions as they teach a virtual agent. This paper extends an exploratory data mining methodology for assessing and comparing students' learning behaviors from these interaction traces. The core algorithm employs sequence mining techniques to…

This article presents a comprehensive examination of panel data for 1,847 consumers and 2,209 brands of "biscuits" (a total of 76,682 records) in which matching analysis is employed to define brand substitutability and potential product clusters within the overall category. The results indicate that, while brands performed as expected as perfect…

The study investigated academic, behavioral, and psychological test performance of children diagnosed as emotionally disturbed, minimally brain injured, of dull normal intelligence, or suffering from a specific learning disability, respectively. Participating were 132 children, whose mean age was 9 years, 7 months. Multidisciplinary evaluation was…