Intelligent tutoring systems (ITSs) have consistently been shown to improve the educational outcomes of students when used alone or combined with traditional instruction. However, building an ITS is a time-consuming process which requires specialized knowledge of existing tools. Extant authoring methods, including the Cognitive Tutor Authoring…

Although visual representations are generally beneficial for learners, past research also suggests that often only a subset of learners benefits from visual representations. In this work, we designed and evaluated anticipatory diagrammatic self- explanation, a novel form of instructional scaffolding in which visual representations are used to…

We report on a research study conducted within a transition-to-proof course for mathematics majors at a large public university. Within the course, students explored famously unproven conjectures and reflected on how their perspectives of mathematics changed through this exploration (if at all). In this report we share students' takeaways from the…

We investigated the effects of proximal grouping of numbers, problem-solving goals to make 100, and prior knowledge on students' solution strategies in an online mathematics game. Logistic regression on 857 problem-level data points from 227 middle-school students showed that students were more likely to use productive solution strategies on…

In this paper, we applied a number of clustering algorithms on pretest data collected from 264 high-school students. Students took the pre-test at the beginning of a 5-week experiment in which they interacted with an intelligent tutoring system. The primary goal of this work is to identify clusters of students exhibiting similar knowledge…

Prior research shows that self-explanation promotes understanding by helping learners connect new knowledge with prior knowledge. However, despite ample evidence supporting the effectiveness of self-explanation, an instructional design challenge emerges in how best to scaffold self-explanation. In particular, it is an open challenge to design…

Learning analytic models are built upon traces students leave in technology-enhanced learning platforms as the digital footprints of their learning processes. Learning analytics uses these traces of learning engagement to predict performance and provide learning feedback to students and teachers when these predictions signal the risk of failing a…

Many studies have shown that visual representations can enhance student understanding of STEM concepts. However, prior research suggests that visual representations alone are not necessarily effective across a broad range of students. To address this problem, we created a novel, scaffolded form of diagrammatic self-explanation in which students…

Decades of research on engagement, retention, and under-representation in STEM conclude that a better understanding of learner development as a long-term, social process is needed. Social identity theory is increasingly used to understand the interplay between individual development and social structure. The present report summarises findings from…

Prior work has found benefits of interpersonal closeness, or rapport, on student learning, but has primarily investigated its impact on learning outcomes, not learning processes. Moreover, such work often analyzes the direct impact of dyadic features like rapport on learning, without considering the role played by individual factors, such as…

Within the context of complex cognitive processing and educational interventions, Woolfolk (2016) makes reference to problem solving acquisition, problem solving retention, and problem solving transfer. In each of the aforementioned types of problem solving activities, problem identification and problem representation (reflecting procedural…

This research targets children's informal strategies and knowledge of fractions by examining their ability to create, interpret, and connect representations in doing and communicating mathematics when solving fractions tasks. Our research group followed a constant comparative method to analyze clinical interviews of children in grades 2-6 solving…

In this paper, we describe an experience within mathematics teacher preparation that engages preservice teachers (PSTs) in Making and design practices that we hypothesized would inform their conceptual and pedagogical thinking. With a focus on the design of new tools to support mathematics teaching and learning, this Learning by Design experience…

The language that students use with whole numbers can be insufficient when learning integers. This is often the case when children interpret addition as "getting more" or "going higher." In this study, we explore whether instruction on mapping directed magnitudes to operations helps 88 second graders and 70 fourth graders solve…

We built on two cognitive and three motivational theoretical constructs to create a combined intervention aiming to improve course achievement and retention in STEM for first-year ("gateway") biology students. Participants were 350 students in one of 8 conditions or a no-treatment control group. Messages supporting cognition and…