Abstract
Cross-cultural psychological research is essential to address the WEIRD (Western, Educated, Industrialized, Rich, and Democratic) bias in psychology. Traditional cross-cultural research often relies on Western-centric theories which may not adequately capture cultural differences beyond East-West comparisons. This tutorial introduces Cultural Classification Models (CCMs), interpretable machine learning models designed to explore cultural differences between countries by distinguishing between participants from different cultures on a cross-cultural dataset. CCMs offer a data-driven approach to quantify cultural distances and identify key variables that differentiate cultures. This tutorial provides a step-by-step guide in R to build CCMs using Random Forests, and derive indices of cultural distance relative to the US and China, using data from Schwartz’s cultural values in the World Values Survey (Wave 6). The tutorial emphasizes the importance of cross-validation, data preprocessing, and feature importance in machine learning, demonstrating how CCMs can enhance the exploration of cultural differences in psychological research, and providing a framework outside WEIRD cultural comparisons for exploring cultural dynamics in a more nuanced and comprehensive manner.
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 3.0 License.