Large Language Models have recently achieved high performance on many writing tasks. In a recent study, math word problems in Carnegie Learning's MATHia adaptive learning software were rewritten by human authors to improve their clarity and specificity. The randomized experiment found that emerging readers who received the rewritten word problems…

This study aimed to assess and compare the development of mathematical procedures on the part of Grade 7 students using an intelligent tutoring system on a digital platform. The sample comprised 96 students from Khon Kaen University Demonstration School, Thailand, divided equally into experimental and control groups. The experimental group worked…

Reducing learning time or training time in intelligent tutors is a challenging research problem. In this study, we aim to reduce training time while maintaining student performance in intelligent tutors. We propose a Deep Reinforcement Learning (DRL) based method to determine when students need more training and when they don't. We design an…

Caregiver involvement in homework is a key contributor to student success, yet its interaction with intelligent tutoring systems remains underexamined. To address this gap, we conducted a technology probe study exploring how a conversational support tool might enhance caregiver assistance during remote math homework within tutoring systems.…

A one-on-one dialogue-based mathematics intelligent tutoring system (ITS) for learning multiplication and division of fractions was developed and evaluated in this study. This system could identify students' error types and misconceptions in real-time by using a block-based matching method. The adaptive dialogue-based instruction was supported by…

We present a recent randomized field trial delivered in Carnegie Learning's MATHia's intelligent tutoring system to a sample of 12,374 learners intended to test whether rewriting content in a selection of so-called "word problems" improves student mathematics performance within this content, especially among students who are emerging as…

Artificial intelligence (AI) shows increasing potential to improve mathematics instruction, yet integrative quantitative evidence currently is lacking on its overall effectiveness and factors influencing success. This systematic review and meta-analysis investigate the effectiveness of AI on improving mathematics performance in K-12 classrooms…

Determining "when" and "whether" to provide personalized support is a well-known challenge called the assistance dilemma. A core problem in solving the assistance dilemma is the need to discover when students are unproductive so that the tutor can intervene. Such a task is particularly challenging for open-ended domains, even…

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…

Technology-enhanced learning generally focuses on the cognitive rather than the affective domain of learning. This multi-method evaluation of the INBECOM project (Integrating Behaviourism and Constructivism in Mathematics) was conducted from the point of view of affective learning levels of Krathwohl "et al." (1964). The research…

When implementing large-scale educational computing initiatives (e.g., One Laptop Per Child) it is vital to allocate resources for training, support, and device deployment judiciously. One question that arises is how learners' engagement with online educational resources is affected by receiving a new computer; do the benefits justify the costs?…

The Cognitive Tutor Algebra I (CTAI) curriculum, which includes both textbook and online components, has been shown to boost student learning by about 0.2 standard deviations in a randomized effectiveness trial. Students who were assigned to the experimental condition varied substantially in how, and how much, the used the online component of…

Much debate surrounds the effectiveness of the common educational practice of homework (Cooper et al., 2006). A randomized-controlled trial has shown that using a web-based homework system that provides immediate feedback to students, while they are doing their mathematics homework, and detailed item reports to teachers significantly improves…

The authors explored the impact of an online tutoring program, Math Whizz (Whizz Education, 2014), on student mathematics achievement at 15 elementary schools. Students participated in the use of the Math Whizz program for the duration of the school year as a supplement to mathematics instruction. The Math Whizz program recorded such information…

Compared to boys, many girls are more aware of a social context in the learning process and perform better when the environment supports frequent interactions and social relationships. For these girls, embodied agents (animated on-screen characters acting as tutors) could afford simulated social interactions in computer-based learning and thereby…