Solving a math word problem (MWP) requires understanding the mathematical components of the problem and an ability to decode the text. For some students, lower reading comprehension skills may make engagement with the mathematical content more difficult. Readability formulas (e.g., Flesch Reading Ease) are frequently used to assess reading…

This paper contains an analysis of some early thinking of 94 young children aged 5 years 7 months to 6 years 5 months. These children were interviewed as part of a larger study of the multiplicative thinking of children who were midway through their first year of school in Australia. They had not been formally taught multiplication or division at…

Missing data presents a significant challenge in Educational Data Mining (EDM). Imputation techniques aim to reconstruct missing data while preserving critical information in datasets for more accurate analysis. Although imputation techniques have gained attention in various fields in recent years, their use for addressing missing data in…

This paper aims to understand how primary students use gestures to solve partition tasks and to what extent these gestures may promote fraction understanding. Analysis of six selected students' answers to partitioning tasks, classroom observation, and post-lesson interviews indicates that co-thought representational gestures play a critical role.…

Knowledge tracing (KT) models predict how students will perform on future interactions, given a sequence of prior responses. Modern approaches to KT leverage "deep learning" techniques to produce more accurate predictions, potentially making personalized learning paths more efficacious for learners. Many papers on the topic of KT focus…

The increasing use of complex machine learning models in education has led to concerns about their interpretability, which in turn has spurred interest in developing explainability techniques that are both faithful to the model's inner workings and intelligible to human end-users. In this paper, we describe a novel approach to creating a…

This paper analyses learners' common errors in simplifying algebraic problems. 102 Grade 10 learners from three rural schools in South Africa participated in the study. Following a quantitative approach, content analysis of learners' responses to algebraic tests revealed that while learners commit several errors in algebraic problems, encoding and…

Mathematical problem-solving places heavy demands on children's developing working memory capacity. This review examines how offloading numerical information using embodied (e.g. finger counting) or external tools (e.g. manipulatives) can reduce cognitive load and improve mathematical task performance. Strategic offloading emerges in childhood;…

Collaborative Problem Solving (CPS) is a vital 21st-century skill that integrates social and cognitive processes to achieve shared goals. Despite its importance, understanding how communication dynamics shape individual learning outcomes in CPS tasks remains a challenge, particularly in virtual settings. To address this gap, this study analyzes…

Research suggests that collaborative learning may enhance the benefits to learners when solving cognitively demanding tasks. However, there are concerns about how students with different achievement and engagement levels perceive these benefits. This study examines how students with varying achievement and engagement levels respond to…

In this paper, we raise questions about the role of student empathy and compassion when engaging with social and environmental justice issues -- significant in a world where challenges associated with such disruptions are faced daily. We draw on data from a larger, nationally funded study on enabling students' critical mathematical thinking. These…

Mathematical problem-posing (MPP) offers an alternative to teacher-directed approaches by encouraging students to create and solve their own problems. While MPP is supported by the Australian Curriculum and empirical research has increased over the last decade, implementation in classrooms is still limited. Using The Theory of Practice…

Large Language Models (LLMs) hold promise as dynamic instructional aids. Yet, it remains unclear whether LLMs can replicate the adaptivity of intelligent tutoring systems (ITS)--where student knowledge and pedagogical strategies are explicitly modeled. We propose a prompt variation framework to assess LLM-generated instructional moves' adaptivity…

Recent research on more comprehensive models of student learning in adaptive math learning software used an indicator of student reading ability to predict students' tendencies to engage in behaviors associated with so-called "gaming the system." Using data from Carnegie Learning's MATHia adaptive learning software, we replicate the…

Students' effort and emotions are important contributors to math learning. In a recent study evaluating the efficacy of MathSpring, a scalable web-based intelligent tutoring system that provides students with personalized math problems and affective support, system usage data were collected for 804 U.S. 10-12-year-olds. To understand the patterns…