Automated image analysis has received increasing attention in social scientific research, yet existing scholarship has mostly covered the application of supervised learning to classify images into predefined categories. This study focuses on the task of unsupervised image clustering, which aims to automatically discover categories from unlabelled…

To meet the national and international call for creative and innovative engineers, many engineering departments and classrooms are striving to create more authentic learning spaces where students are actively engaging with design and innovation activities. For example, one model for teaching innovation is Innovation-Based Learning (IBL) where…

This study aimed to cluster learners based on the structures of the knowledge maps they created. Learners drew their own knowledge maps to reflect their learning activities. Our system collected individual knowledge maps from many learners and clustered them to generate an integrated version of the knowledge maps of each cluster. We applied the…

Studies on engagement and learning design in Massive Open Online Courses (MOOCs) have laid the groundwork for understanding how people learn in this relatively new type of informal learning environment. To advance our understanding of how people learn in MOOCs, we investigate the intersection between learning design and the temporal process of…

Collaborative problem-solving (CPS) as a key competency required in the 21st century. There has been an increasing need to understand CPS since it involves not only cognitive but also social processes, and thus its process is difficult to examine. Recent research has highlighted that computer-based learning environments provide an opportunity for…

We propose a data driven method for decomposing population level learning curve models into mutually exclusive distinctive groups each consisting of similar learning trajectories. We validate this method on six knowledge components from the log data from an online tutoring system ASSISTment. Preliminary analysis reveals interpretable patterns of…

The open nature of Massive Open Online Courses (MOOCs) attracts a large number of learners with different backgrounds, skills, motivations, and goals. This has brought a need to understand such heterogeneity in populations of MOOC learners. Categorizing these learners based upon their interaction with the course can help address this need and…

User clustering algorithms have been introduced to analyze users' learning behaviors and help to provide personalized learning guides in traditional Web-based learning systems. However, the explicit and implicit coupled interactions, which means the correlations between user attributes generated from learning actions, are not considered in these…

Social anxiety in learning is prevalent amongst traditional-age students and has a marked effect on their engagement with higher education. It receives little attention from academic or support services and there is a presumption that students will manage their anxieties. Yet it is unclear what psychosocial resources they might bring to this task…

It is well known that the regulation of processes is an important factor in problem solving from Grade 7 to university level (cf. Mevarech & Kramarski, 1997; Schoenfeld, 1985). We do not, however, know much about the problem-solving competencies of younger children (cf. Heinze, 2007, p. 15). Do the results of studies also hold true for…

Background: A re-analysis of several university-level interview studies has suggested that some students show evidence of a deep and stable approach to learning, along with other characteristics that support the approach. This combination, it was argued, could be seen to indicate a "disposition to understand for oneself." Aim: To…

The teaching and learning of mathematics cannot be understood without considering the resolution of word problems. These kinds of problems not only connect mathematical concepts with language (and therefore with reality) but also promote the learning related to other scientific areas. In primary school, problems are solved by using basic…

New high-frequency, automated data collection and analysis algorithms could offer new insights into complex learning processes, especially for tasks in which students have opportunities to generate unique open-ended artifacts such as computer programs. These approaches should be particularly useful because the need for scalable project-based and…

A. Redish et al. (2007) proposed a reinforcement learning model of context-dependent learning and extinction in conditioning experiments, using the idea of "state classification" to categorize new observations into states. In the current article, the authors propose an interpretation of this idea in terms of normative statistical inference. They…