Search Results (309)

Self-assessment plays an important role in the teaching-learning process, as it helps students actively construct their own knowledge. This article aims to develop a methodology for creating quizzes for e-learning platforms, with the goal of addressing students’ difficulties in mathematics and promoting active learning. The proposed methodology begins with identifying the processes that students need to activate and analyzing the most common errors related to them. A key element is the integration of the MATH taxonomy to determine what is necessary or what is intended to be assessed with this type of question. In addition, Niss's skills are used, i.e., the skills that students need to answer these questions. An important part of the methodology is also the selection of mathematical language, which can be simple and close to everyday language or more sophisticated, verbal, symbolic or mixed, depending on the educational objective. This approach aims to create diagnostic and personalized questions designed to support self-assessment and independent learning in digital environments. Full article

The rapid integration of artificial intelligence (AI) into educational systems is transforming how student performance is analysed and how educational policies are informed by large-scale data. Within this context, machine learning techniques are increasingly used to identify patterns associated with academic success and educational inequality. However, the use of predictive algorithms in education also raises important questions regarding transparency, fairness, and potential algorithmic bias. This study examines the predictive performance and fairness implications of machine learning models used to identify academically resilient students using data from the Programme for International Student Assessment (PISA) 2022. The analysis is based on a dataset containing more than 600,000 student observations across multiple national education systems. Academic resilience is operationalised following the OECD framework, identifying students who belong to the lowest quartile of the socioeconomic status index (ESCS) within their country while simultaneously achieving mathematics performance in the top quartile (PV1MATH). A predictive framework incorporating six supervised learning algorithms—Logistic Regression, Random Forest, Gradient Boosting, XGBoost, LightGBM, and CatBoost—was implemented. The modelling pipeline includes data preprocessing, missing value imputation, class imbalance correction using SMOTE, and model evaluation through multiple classification metrics, including accuracy, F1-score, and the area under the ROC curve (AUC). In addition, fairness diagnostics are conducted to examine potential disparities in prediction outcomes across gender groups, while feature importance analysis and SHAP-based explanations are used to interpret the contribution of key predictors. The results indicate that ensemble-based models achieve the highest predictive performance, particularly those based on gradient boosting techniques. At the same time, the analysis reveals that socioeconomic status, migration background, and school repetition constitute the most influential predictors of academic resilience. Although gender displays relatively low predictive importance, measurable differences in positive prediction rates across gender groups suggest the presence of potential algorithmic disparities. These findings highlight the importance of integrating fairness evaluation, transparency, and interpretability into educational data science workflows. The study contributes to ongoing discussions on the responsible use of artificial intelligence in education by emphasising the need for governance frameworks capable of ensuring that algorithmic systems support equity-oriented educational policies. Full article

The objective of this study is to develop and incorporate a multidisciplinary engineering design experience into an academic success and professional development course that aims to retain non-calculus-ready first-year engineering students. The project followed the five-step engineering design process using knowledge from multiple engineering disciplines. Students were tasked to design a scale model of a safe, sustainable, and cost-efficient oil derrick with PASCO kits, engage in discussion to consider societal, global, cultural, and further factors in design, practice an elevator pitch with entrepreneurship specialists from the university start-up incubator, and present the final design to a multidisciplinary judge panel from academia and industry in engineering, math, social science, and business at a Poster Expo. This project-based learning aligned with the student outcomes of ABET and the Engineering for One Planet framework for sustainability education in engineering. Opportunities and challenges of this multidisciplinary learning experience were analyzed using triangulated data sources from student course performance, a student perception survey (N = 16; Cronbach’s α = 0.959), and student retention data. Results showed a positive student learning experience with 88% of students reporting that the multidisciplinary design experience was positive to their learning and increased their interest in engineering. Ninety-four percent of student retention in engineering was reported by the end of the semester (N = 17). Full article

With the increasing integration of computer technologies into education, accurately modeling students’ knowledge mastery has become a central problem in intelligent education systems. However, existing cognitive diagnosis models often suffer from sparsity in the knowledge–item association matrix (Q-matrix) and limited model capacity, which restrict their ability to capture complex student–item interaction patterns. Collaborative filtering–based approaches further exhibit insufficient capability in modeling fine-grained cognitive relationships, leading to reduced diagnostic accuracy. To address these limitations, this study proposes a cognitive diagnosis model enhanced by an augmented knowledge association matrix, termed CAG-NCD. The proposed model refines the Q-matrix to improve the expressiveness of item–knowledge correspondences and employs nonlinear interaction functions to capture relational features in students’ response processes. Specifically, convolutional neural networks are used to extract local semantic patterns from student–item interactions, while graph convolutional networks model the global structural dependencies among knowledge points. By jointly integrating semantic and structural information, the model effectively captures complex dependency relationships. Experimental results show that CAG-NCD achieves performance improvements of 3.7% on the FrcSub dataset and 4.5% on the Math dataset, significantly reducing prediction errors and enhancing the interpretability and accuracy of cognitive diagnosis across multiple datasets. Full article

Despite consensus in the mathematics education literature regarding the mutually dependent components of math proficiency, as well as the importance of their development, most elementary-aged students in the United States demonstrate a lack of proficiency in math according to national assessment data. Whole number knowledge, which includes skills in computation and word-problem solving, is understood to be a critical foundation for the development of later math skills. This study used a multiple-baseline experimental design to evaluate the impacts of an evidence-based mathematics intervention, Accelerating Mathematics Performance with Practice Strategies (AMPPS), on third- through fifth-grade students’ skills with complex computation, as well as on their word-problem-solving performance. Furthermore, we evaluated effects on students’ math self-concept. Five students identified to have difficulties in math received AMPPS in a one-on-one, in-person format. The results of the study were mixed. For example, when using visual analyses as our primary analytic method, these analyses did not show robust intervention effects on students’ computation skills but did show at least some improvement for most students’ word-problem-solving skills. Additionally, supplemental analyses comparing student growth to national and school-based norms suggested that all participants seemed to benefit from the intervention, but these analyses were not intended to examine experimental causality. Despite study limitations and a lower than optimal number of AMPPS sessions (dosage) provided to students, the present study offers several directions for future research, as well as possible implications for practitioners regarding intervention selection, intensity, and evaluation. The findings will also be discussed in the context of conducting systematic replication studies, which are essential for understanding the generality of a given phenomenon (e.g., an effect of a school-based intervention) across a wide range of situations and conditions. Full article

Math anxiety, or a student’s lack of confidence in learning mathematics, is one of the emotional dimensions with the greatest impact on mathematics education. Sociological factors such as sex and age, demographic aspects like cultural characteristics, and emotional variables such as general anxiety have been identified as significantly influencing math anxiety. This study conducts quantitative, descriptive, correlational, and regression analyses of the influence of sex, age, and general anxiety on math anxiety in a sample of 185 Spanish elementary students. It also examines whether the effects of age and general anxiety on math anxiety differ by sex. For this purpose, students’ responses to a quantitative questionnaire are analyzed. The instrument combines two validated scales: (i) STAIC T-Anxiety, measuring general anxiety, and (ii) AMAS, measuring math anxiety. Results show that students exhibit moderate average math anxiety, which is not significantly affected by sex. However, significant correlations between math anxiety, age, and general anxiety were found, independent of sex. The study highlights the need to design corrective measures for math anxiety and suggests lines for future research. Full article

Most pre-trained language representation models are designed to encode contextualized semantic information for general language processing tasks. However, they are insufficient for math word problem (MWP) solving, which requires not only linguistic syntax and semantic understanding but also numerical reasoning. In this work, we introduce SSN4Solver, a deep neural solver that improves MWP-solving performance by symmetrically fusing syntax, semantics, and numeracy representations within its contextual encoder. Our approach jointly captures syntactic structures from dependency trees, semantic features from part-of-speech tags, and the attributes and relations of numerical entities. By treating these heterogeneous information sources in a balanced and aligned manner, SSN4Solver constructs a rich, multi-faceted representation for MWP solving without introducing substantial computational overhead, empowering human–computer interaction (HCI) applications such as adaptive educational interfaces and intelligent tutoring systems. Extensive experiments demonstrate that SSN4Solver outperforms existing baseline models. In addition, a visualization scheme is designed to elucidate how the three types of representations contribute to the solving process. SSN4Solver thus offers a scalable solution, contributing to the development of HCI systems that are both intelligent and mathematically effective. Full article

Previous research indicates that cognitive and affective-motivational factors, along with gender, influence students’ educational choices, especially regarding STEM tracks. However, few longitudinal studies have examined these factors during middle school, a critical stage in shaping future academic trajectories. This study investigated the longitudinal contribution of gender, cognitive abilities, and affective-motivational factors, such as self-concept, math interest, and math anxiety, in predicting students’ school choice between STEM and non-STEM tracks at the end of middle school. Data were collected from 159 Italian students, followed from seventh to eighth grade. Findings indicated that gender and positive attitudes toward math were strongly associated with STEM school choice. Boys were more likely than girls to choose STEM tracks (b = 5.048). Higher levels of math self-concept (b = 4.848) and interest (b = 0.887) significantly predicted the likelihood of choosing a STEM school. These results highlight how gender and affective-motivational factors shape educational pathways during adolescence. Full article

Multilingual learners (MLs) in U.S. schools continue to face systemic inequities shaped by monoglossic instructional ideologies and a deficit orientation towards their linguistic and cultural resources. Translanguaging pedagogy has emerged as a promising response, but it remains underexplored in STEM contexts. This study presents a systematic meta-synthesis of 20 U.S.-based empirical studies examining how translanguaging has been conceptualized and enacted in K–12 STEM classrooms with MLs, using an interpretive approach. The review identified four overarching themes. First, research and practice gaps reveal contextual, conceptual, and disciplinary limitations, particularly a lack of translanguaging work in math, early elementary settings, and English-dominant classrooms. Second, translanguaging was conceptualized as a syncretic and disciplinary practice, challenging rigid boundaries between languages, discourses, and modes while positioning MLs’ full repertoires as generative of disciplinary knowledge. Third, students and teachers were positioned as local agents of knowledge and practice. MLs were framed as designers of disciplinary meaning while teachers acted as collaborators and local policymakers. Fourth, the review identified persisting challenges, including language separation ideologies, narrow interpretations of translanguaging, and policy constraints. This synthesis contributes an interdisciplinary, equity-oriented framework bringing second language acquisition and STEM education, centering MLs as legitimate epistemic participants in STEM. Full article

Developing an engineering identity is critical for supporting students’ engineering career pathways. Yet, migratory adolescents are often not afforded engineering experiences to support that identity formation. Early experiences in math and science often serve as gateways to engineering careers; examining students’ attitudes and beliefs in these subjects is essential to understanding identity formation. This study took an exploratory approach to examine how migratory adolescents’ math and science attitudes and beliefs, specifically their interest, recognition, and performance beliefs, contributed to developing an aspirational engineering identity. Mediation analysis was used to explore how math and science interest, recognition, and performance beliefs shaped the engineering identity formation of 227 migratory adolescents. Results show that math and science interest served as both a direct pathway to engineering identity and as the essential mediator linking performance beliefs and recognition to engineering identity development. Performance beliefs and recognition operated as interchangeable predictor variables but supported engineering identity through their influence on students’ interest in math and science. Multiple pathways emerged for fostering an engineering identity among migratory adolescents, rather than a singular path. These findings highlight the importance of cultivating math and science interest as a key mechanism for supporting engineering aspirations and informing future educational interventions for this underrepresented group. Full article

Educational drones have become increasingly important in education and research due to their affordability, user-friendly design and control, and potential use as tools in STEM (Science, Technology, Engineering, and Math) learning. For example, CoDrone EDUs are used to teach basic programming principles and drone control to high school or university students. As drones in real-world applications often collaborate to solve problems, controlling multiple educational drones in a team is crucial and beneficial for enhancing students’ problem-solving and design skills. However, these educational drones primarily rely on one-to-one control via a radio-frequency remote controller, and programming libraries for coordinating multi-drone missions are limited, posing challenges for students or developers in controlling them effectively. To address the lack of control in missions with multiple educational drones, we present a drone control station (DCS), featuring a centralized architecture that connects and controls various drones. We first develop scenarios and use cases that utilize multiple drones, specifying the system requirements. We then design conceptual models and architectures for the DCS. Next, we implement the DCS and evaluate whether it achieves the team missions. Experimental results show that the DCS with the centralized architecture is suitable for team missions with multiple educational drones. We expect the approach in our work to serve as a method for controlling multi-drone missions in an educational environment. Full article

This work explores user needs for educational games and gamification that incorporates Generative Artificial Intelligence (GenAI). As GenAI is increasingly incorporated in educational settings, we must consider both the wide-spanning literature on gamification and games that have been shown to benefit learning, and characterize the needs and desires of relevant stakeholders in developing educational games that incorporate GenAI generally, and specifically for higher education. A mixed-methods questionnaire inquired 345 undergraduate students about their perceptions, use patterns, needs, and desires related to GenAI, educational and non-educational games, and text-based games. GenAI tools are widely used for educational purposes already, but mostly as a supplementary source. Despite the wide use, participants expressed being concerned with accuracy, transparency, and quality. Participants also expressed a desire for an educational game/tool to have scaffolded interactions and to help with learning material in math, science, and language arts. Taken together the findings provide a road map and specific recommendations for developing an educational game incorporating GenAI. The roadmap includes instructional design (i.e., the gamified tools’ content and type(s) of instruction and interaction) through information regarding preferred platforms, game genres, gamified properties (e.g., characters, challenges), and lastly, clear information about concerns students have related to trust and equity that will need to be addressed in an educational game incorporating GenAI. Full article

In this study, we aimed to investigate the cognitive and affective-emotional factors underlying math achievement in a sample of 169 Japanese elementary school children. Using structural equation modeling, we examined the contributions of fluid and crystallized intelligence, verbal and spatial working memory, and affective-emotional variables, including general anxiety, test anxiety, math anxiety, and math self-efficacy. We found intelligence to be a strong positive predictor of math achievement, while among the affective-emotional variables, math self-efficacy emerged as the only significant predictor of math achievement. Interestingly, intelligence mediated the association between affective-emotional factors, such as math anxiety and self-efficacy, highlighting its central role in children’s math achievement. These findings underscore the strong relationship between intelligence and self-efficacy in educational contexts, suggesting that self-efficacy is closely linked to cognitive abilities to support children’s success in math. Educational implications are discussed, emphasizing the need to strengthen math self-efficacy alongside cognitive abilities. Full article

Inclusive AI-mediated mathematics education for students with learning difficulties refers to a human-centered approach to mathematics teaching and learning that uses artificial intelligence (AI), adaptive technologies, and data-rich environments to support learners who experience persistent challenges in mathematics. These challenges may take the form of a formally identified developmental learning disorder with impairment in mathematics, broader learning difficulties, low and unstable achievement, irregular engagement, or heightened mathematics anxiety that places students at risk of disengagement and poor long-term outcomes. This approach integrates early screening, personalized instruction, and affect-aware support to address both cognitive difficulties and the emotional burden associated with mathematics anxiety. Situated within digitally augmented schools, homes, and community spaces typical of smart cities, it seeks to reduce stress and anxiety, prevent the reproduction of educational inequalities, and promote equitable participation in science, technology, engineering, and mathematics (STEM) pathways. It emphasizes Universal Design for Learning (UDL), ethical and transparent use of learner data, and sustained collaboration among teachers, families, technologists, urban planners, and policy-makers across micro (individual), meso (school and community), and macro (urban and policy) levels. Crucially, AI functions as decision support rather than replacement of pedagogical judgment, with teachers maintaining human-in-the-loop oversight and responsibility for inclusive instructional decisions. Where learner data include fine-grained logs or affect-related indicators, data minimization, clear purpose limitation, and child- and family-friendly transparency are essential. Implementation should also consider feasibility and sustainability, including staff capacity and resource constraints, so that inclusive benefits do not depend on high-cost infrastructures. Full article

Tertiary mathematics teaching is predominantly face-to-face, yet large, diverse cohorts and limited contact hours constrain opportunities for individually paced practice and timely feedback. We developed three bespoke, self-paced online numeracy modules, each targeting a specific mathematical concept and disciplinary context. Module design was informed by learning theory (constructivist, active learning, Universal Design for Learning, inclusive learning practices). We ran a qualitative pilot study to gain insight into user perceptions of modules in terms of engagement and perceived learning support, conducting semi-structured interviews with undergraduate science students (n = 11) and educators (n = 7). We applied thematic analysis to interview data, which generated the following insights. Students—many reporting high mathematics anxiety—responded positively, valuing low-stakes iterative practice, clear stepwise scaffolding, multimodal presentation, contextualized examples aligned to their course, and a supportive instructor voice. These features were described as reducing anxiety, reframing errors as part of learning, and supporting inclusion, despite prevalent math avoidance in the cohort. Staff feedback was more cautious, recognizing similar strengths but focusing on areas for improvement. We argue that bespoke, contextualized modules can augment face-to-face instruction by delivering individualized pacing and immediate feedback at scale, while contributing to the creation of an accessible, inclusive, supportive learning environment. Future work should quantify learning outcomes, track affective changes longitudinally, and isolate contributions of specific design features across diverse cohorts and disciplines. Full article