A machine learning model of cultural change: Role of prosociality, political attitudes, and Protestant work ethic.

Abstract

What attitudes, values, and beliefs serve as key markers of cultural change? To answer this question, we examined 221,485 respondents from the World Values Survey, a multi-wave cross-country survey of people's attitudes, values and beliefs. We trained a machine learning model to classify respondents into seven waves (i.e., periods). Once trained, the machine learning model identified a separate group of 24,611 respondents' wave with a balanced accuracy of 77%. We then queried the model to identify the attitudes, values, and beliefs that contributed the most to its classification decisions, and therefore, served as markers of cultural change. These included religiosity, social attitudes, political attitudes, independence, life satisfaction, Protestant work ethic, and prosociality. Although past research in cultural change has discussed decreasing religiosity and increasing liberalism and independence, it has not yet identified Protestant work ethic, political orientation, and prosociality as values relevant to cultural change. Thus, the current research points to new directions for future research on cultural change that might not be evident from either a deductive or an inductive approach. This research illustrates that the abductive approach of machine learning, which focuses on the most likely explanations for an outcome, can provide novel insights. Public SignificanceStatement. This research found that in recent years, people around the world have been becoming less religious and more liberal in their social attitudes and political orientation. People have been valuing independence more, although there appears to be a decline in independence in the last few years. The extent to which people emphasize hard work, thrift, and acting in a prosocial manner has also declined in recent years.

Trends in the thematic landscape of HR analytics research: a structural topic modeling approach

“…Studies have investigated the model of cultural change in businesses using clustering techniques like gradient boost (Sheetal and Savani, 2021). Studies have demonstrated the value of applying analytics tools to human resource processes, such as people selection processes like MCDM (Maghsoodi et al ., 2020).…”

Using machine learning to analyze longitudinal data: A tutorial guide and best‐practice recommendations for social science researchers

“…As HILDA has a large proportion of missing values, we are left with gradient boosting, which can handle missing values (e.g. Sheetal & Savani, 2021). We used the XGBoost implementation of gradient boosting (Chen & Guestrin, 2016), which constructs boosted decision trees around the missing values and does not require missing values to be imputed.…”

The psychology of cultural change: Introduction to the special issue.

“…Thus, accounting for autocorrelation is crucial when using time series data to assess claims regarding the causes of specific cultural changes (for more detailed arguments and specific recommendations see Jebb et al, 2015;Varnum & Grossmann, 2017). Some articles also adopt what is arguably another gold standard for such work, making out-of-sample predictions (Sheetal & Savani, 2021;Stavrova et al, 2021), including predictions for the future (Rotella et al, 2021). This approach will become increasingly common in this emerging field.…”

“…Some articles also adopt what is arguably another gold standard for such work, making out-of-sample predictions (Sheetal & Savani, 2021; Stavrova et al, 2021), including predictions for the future (Rotella et al, 2021). This approach will become increasingly common in this emerging field.…”

“…These pieces capture a range of theoretical perspectives that have been brought to bear on how and why cultures change over time, including insights from evolutionary psychology (Jackson et al, 2021; Kusano & Kemmelmeier, 2021; Pan et al, 2021), behavioral ecology (Rotella et al, 2021), cultural evolution (Schaller & Muthukrishna, 2021), and socioecological psychology (Buttrick & Oishi, 2021). The special issue also highlights the diversity of methodological approaches in this emerging field ranging from computational modeling (Jung et al, 2021; Schaller & Muthukrishna, 2021; Pan et al, 2021), to machine learning (Sheetal & Savani, 2021; Stavrova et al, 2021), to time series analyses (Charlesworth & Banaji, 2021; Chan et al, 2021; Götz et al, 2021; Kusano & Kemmelmeier, 2021; Rotella et al, 2021).…”