Tracking historical changes in trustworthiness using machine learning analyses of facial cues in paintings

Abstract

Social trust is linked to a host of positive societal outcomes, including improved economic performance, lower crime rates and more inclusive institutions. Yet, the origins of trust remain elusive, partly because social trust is difficult to document in time. Building on recent advances in social cognition, we design an algorithm to automatically generate trustworthiness evaluations for the facial action units (smile, eye brows, etc.) of European portraits in large historical databases. Our results show that trustworthiness in portraits increased over the period 1500-2000 paralleling the decline of interpersonal violence and the rise of democratic values observed in Western Europe. Further analyses suggest that this rise of trustworthiness displays is associated with increased living standards.

Fig. 1. Evolution of ratings of perceived trustworthiness in England across time.

a Example of faces detected in portraits from the National Portrait Gallery and estimated as being perceived as lowly trustworthy (top; Thomas Cranmer by Gerlach Flicke, 1545-1546, NPG 535 All rights reserved © National Portrait Gallery, London) and estimated as being perceived as highly trustworthy (bottom; Sir Matthew Wood by Arthur William Devis, 1815-1816, NPG 1481 All rights reserved © National Portrait Gallery). b Evolution of ratings of perceived trustworthiness in the National Portrait Gallery (for representation purposes, in this Figure, evaluations of perceived trustworthiness were fitted by a local polynomial regression with a span of 0.75 and adjusted for perceived dominance) and GDP per capita in England. (log-transformed for representation purposes). Source data are provided as raw data and scripts on the online depository.

Fig. 2. Effect of time and affluence on ratings of perceived trustworthiness across time.

Time was associated with an increase of ratings of perceived trustworthiness displays in both the National Portrait Gallery (a data are aggregated by decade; regression line corresponds to the analysis on individual portraits) and the Web Gallery of Art (b)—data are aggregated country and by decades; regression line corresponds to the analysis on individual portraits). Increased GDP per capita predicted increased ratings of perceived trustworthiness displays better than time only-models both in the National Portrait Gallery (c data are aggregated by GDP; regression line corresponds to the analysis on individual portraits) and the Web Gallery of Art (d data are aggregated by country and GDP; regression line correspond to the analysis on individual portraits). Data are represented as mean values, error bars represent standard error to the means, the red line corresponds to the estimated effect in the regression adjusting for gender, age (for the National Portrait Gallery only) and perceived dominance, the shaded area represents the standard error to the mean of these effects. Source data are provided as raw data and scripts on the online depository.