The utilization of learning analytics to identify at-risk students for early intervention has exhibited promising results. However, most predictive models utilized to address this issue have been based on non-probabilistic machine learning models. In response, this study incorporated probabilistic machine learning for two reasons: (1) to facilitate the inclusion of domain knowledge, and (2) to enable the quantification of uncertainty in model parameters and predictions. The study developed a five-stage, probabilistic logistic regression model to identify at-risk students at different stages throughout the academic calendar. Rather than predicting a student’s final or exam mark, the model was focused on predicting the at-risk probabilities for subsequent assessments—specifically, the probability of a student failing an upcoming assessment. The model incorporated student engagement data from Moodle, as well as demographic and student performance data. The study’s findings indicate that the significance and certainty of student engagement and demographic variables decreased after incorporating student-performance variables, such as assignments and tests. The most effective week for identifying at-risk students was found to be week 6, when the accuracy was 92.81%. Furthermore, the average level of uncertainty exhibited by the models decreased by 60% from stage 3 to 5, indicating more reliable predictions at later than earlier stages. The study highlights the potential of a probabilistic machine learning model to aid instructors and practitioners in identifying at-risk students, and thereby to enhance academic outcomes.

This study comprehensively analyses how AI tools scaffold and share metacognitive processes, thereby facilitating students’ learning in STEM classrooms through a mixed-method research synthesis combining bibliometric analysis and systematic review. Using a convergent parallel mixed-methods design, the study draws on 135 peer-reviewed articles published between 2005 and 2025 to map publication trends, author and journal productivity, keyword patterns, and theoretical frameworks. Data were retrieved from Scopus and Web of Science using structured Boolean searches and analysed using Biblioshiny and VOSviewer. Guided by PRISMA 2020 protocols, 24 studies were selected for in-depth qualitative review. Findings show that while most research remains grounded in human-centred conceptualisations of metacognition, there are emerging indications of posthumanist framings, where AI systems are positioned as co-regulators of learning. Tools like learning analytics, intelligent tutoring systems, and generative AI platforms have shifted the discourse from individual reflection to system-level regulation and distributed cognition. The study is anchored in Flavell’s theory of metacognition, General Systems Theory, and posthumanist perspectives to interpret this evolution. Educational implications highlight the need to reconceptualise pedagogical roles, integrate AI literacy in teacher preparation, and prioritise ethical, reflective AI design. The review provides a structured synthesis of theoretical, empirical, and conceptual trends, offering insights into how human–machine collaboration is reshaping learning by scaffolding and co-regulating students’ metacognitive development in STEM education.

This paper explores the value of indigenous games in the teaching and learning of word problems in Grade 4 mathematics. In particular, the paper explains how the moves of *kgati (skipping rope) can be used to enhance the teaching and learning of mathematics word problems. Participatory action research (PAR) methodology was used to generate data so as to enable participants to work collaboratively, freely and with confidence. Participants of this study were Grade 4 learners, a head of department, two Grade 4 mathematics teachers, a life skills teacher, a mathematics subject advisor, four parents and three members of the local royal family. The study seeks to answer the question: To what extent can learners use knowledge of the kgati (skipping rope) game to enhance the learning of mathematics word problems? Community cultural wealth (CCW) theory was employed as a lens that acknowledges the huge wealth of knowledge that participants bring from their homes into the classroom. These forms of capitals include aspirational, navigational, social, linguistic, familial and resistant capital which relate to the knowledge learners bring from home and use to tap into word problems. Critical discourse analysis was used to analyse the words of the research team to reach their deeper meanings. The results of the study indicate that learners can interpret, convert and link their indigenous knowledge with mathematics and improve their understanding of mathematics concepts when indigenous knowledge is incorporated. Incorporating kgati moves to learn word problems significantly improved learners’ creativity and imagination. The study further suggests that learners work better when given opportunities for interactive and collaborative activities that relate to their daily practices.

This study addresses the integration of AI-based technologies in education, focusing on secondary school mathematics classrooms. As technology shapes the education landscape, understanding students' perceptions becomes crucial. This research explores secondary school students' views on integrating AI-based ChatGPT in their mathematics education. Employing a mixed-methods design, the study used purposive sampling to select 125 students from senior classes 1, 2, and 3 in two schools. Data were collected through a questionnaire with Likert scale items and semi-structured interviews. Quantitative data were analysed using descriptive statistics, while qualitative responses were thematically analysed. Results revealed students' multifaceted perspectives, highlighting benefits and concerns. Students valued ChatGPT's role in enhancing understanding and problemsolving but expressed reservations about its consistent use and potential limitations. Preferences for adaptive responses and customisation tailored to individual learning styles are evident. Recommendations include comprehensive training, enhancing ChatGPT's adaptability, fostering critical inquiry, addressing ethical considerations, and collaborative policy development.

Euclidean geometry provides an opportunity for learners to learn argumentation and develop inductive and deductive reasoning. Despite the significance of Euclidean geometry for developing these skills, learner performance in mathematics, particularly geometry, remains a concern in many countries. Thus, the current study examined the nature of learners’ errors in Euclidean geometry problem-solving, particularly regarding the theorem for angle at the centre and its applications. Van Heile’s theory of geometric thinking and teacher knowledge of error analysis were used as conceptual frameworks to make sense of the nature of learners’ errors and misconceptions. Using a participatory action research approach, the study was operationalised by five mathematics teachers from four secondary schools in Motheo district in the Free State Province of South Africa and three academics from two local universities. The study analysed 50 sampled midyear examination scripts of Grade 12 learners from four schools. The findings of this study revealed that most learner errors resulted from concepts on Van Heile’s operating Levels 0 and 1, while the questions mainly required Level 3 thinking. The study recommends that teachers determine their learners’ level of geometric thinking and integrate this knowledge in their lesson preparations and material development.

This study explores the multifaceted factors influencing academic performance among undergraduate students enrolled in Science, Technology, Engineering, and Mathematics (STEM) programs at a South African university. Employing a Bayesian hierarchical modelling approach, this research analyses data from 630 students collected over four academic years (2019–2023). The findings indicate that high school mathematics marks and progression rates serve as significant predictors of academic success, confirming the critical role of foundational mathematical skills in enhancing university performance. Interestingly, gender and age were found to have no statistically significant impact on academic outcomes, suggesting that these factors may be less influential in this context. Additionally, socio-economic status, represented by school quintiles, emerged as a substantial determinant of performance, highlighting disparities faced by students from disadvantaged backgrounds. The results underscore the necessity for targeted educational interventions aimed at bolstering the academic capabilities of students entering university, particularly those with weaker mathematics backgrounds. Furthermore, the study advocates for a holistic admissions approach that considers various attributes beyond standardized scores. These insights contribute to the existing literature on STEM education and provide practical recommendations for educators and policymakers aiming to foster equitable academic success among all students.