Classifying East Asian Mathematics Performers: A Machine Learning Approach (Poster 47)

• In Event: AERA Poster Session Sunday 1:30 p.m.
  In Poster Session: Machine Learning Approaches to Enhancing Learning Environments With Artificial Intelligence

Abstract

Mathematics education in East Asia has been widely investigated, with few studies paying attention to the attributes of the low-mathematics performers in the world. Therefore, this study compares four Machine Learning (ML) algorithms, namely Support Vector Machine (SVM), Decision Tree (DT), Logistic Regression (LR), and K-Nearest Neighbours (KNN), in classifying the mathematics performance of East Asian students based on mathematics-specific features from the Programme for International Student Assessment (PISA) 2022 data. The results showed that (1) these four ML algorithms yielded similar predictive performance; (2) mathematics self-efficacy was a salient positive predictor of mathematics performance; and (3) cognitive activation was a salient but negative predictor. Theoretical, methodological, and practical contributions and implications in the context of mathematics are discussed.

Authors

• Yimei Zhang, McGill University

• Maria Cutumisu, McGill University