Does Culture Matter in Predicting Secondary Students' Life Satisfaction? A Machine Learning Approach

• In Event: Large Scale Assessment SIG Virtual Paper Session

Abstract

Life satisfaction is a key component of students’ subjective well-being and has rarely been studied using machine learning (ML) approaches. This study predicts secondary students’ life satisfaction using two supervised ML models, random forest (RF) and k-nearest neighbors (KNN). In consideration of the cultural dimension of individualism versus collectivism, the models were developed based on the UK data and the Japanese data from PISA 2018. Findings show that (1) both models yielded better performance on the UK data; (2) the RF model outperformed the KNN model in both countries; and (3) the variables related to psychological dispositions played the most significant role in prediction. This study highlights the importance of culture and serves as a reference for improving students’ life satisfaction.

Authors

• Zexuan Pan, University of Michigan
  Presenting Author

• Maria Cutumisu, McGill University
  Non-Presenting Author