What is it about?
Transforming the education system and building highly-skilled human capital for a sustainable and competitive knowledge economy have been on UAE’s top policy agenda for the last decade. However, UAE students’ math performance on the Program for International Student Assessment (PISA) has not been promising. In order to improve the quality of schooling, a series of malleable predictive factors are selected and categorized under student approaches to math learning, which are hypothesized as both predictors and outcomes of K12 schooling. Through the analysis using machine learning technique, XGBoost, a latent relationship between student approaches to math learning (i.e. self-system, metacognitive strategies, instructional language skills) and math diagnostic test performance is uncovered and discussed for students from Grade 5 to Grade 9 in Abu Dhabi public schools. This paper details how the analysis results are applied for student behavior and performance prediction, precise diagnosis, and targeted intervention design possibilities. The main purpose of this study is to diagnose challenges that are hindering student math learning in Abu Dhabi public schools, uncover R&D initiatives in AI-driven prediction and EdTech interventions to bridge learning gaps, and to counsel on national education policy refinement.
Featured Image
Photo by Tim Alex on Unsplash
Why is it important?
First of all, the use of machine learning Shapley algorithms for education research is new and has been proven effective to identify the contribution of learning factors matter to Abu Dhabi K12 public school context ; second, this methodology is taking into account the interplay of all learning factors while still predicts which factors are more important, which is different than regression models; third, there is not much research done within the UAE to guide evidence-based education research and intervention recommendations.
Perspectives
This paper has two highlights: 1) student approaches to math learning is the foundation for measurement design. Based on this and the understanding of local school context, measurements defined in this research are already important factors for learning; 2) shapley methodology. Given the interplay of all factors defined, this research found ranking of predictive learning factors on a population level. Additionally, this methodology also allows individual level of prediction, which potentially benefits prediction model for personalised learning product designs.
Xin Miao
Alef Education
Read the Original
This page is a summary of: Evidence and Promises of AI Predictions to Understand Student Approaches to Math Learning in Abu Dhabi K12 Public Schools, Gulf Education and Social Policy Review (GESPR), January 2021, Knowledge E,
DOI: 10.18502/gespr.v1i2.8458.
You can read the full text:
Contributors
The following have contributed to this page
