Moral concerns are differentially observable in language

Language is a psychologically rich medium for human expression and communication. While it is often used in moral psychology as an intermediary between researcher and participant, much of the human experience that occurs through language — our relationships, conversations, and, in general, the everyday transmission of our thoughts — has yet to be studied in association with moral concerns. In order to understand how moral concerns relate to observed language usage, we paired Facebook status updates (N = 107,798) from English-speaking participants (n = 2,691) with their responses on the Moral Foundations Questionnaire, which measures Care, Fairness, Loyalty, Authority, and Purity concerns. Overall, we found consistent evidence that participants’ self-reported moral concerns can be predicted from their language, though the magnitude of this effect varied considerably among concerns. Across a diverse selection of Natural Language Processing methods, cross-validated R2 values ranged from 0.04 for predicting Fairness concerns to 0.21for predicting Purity concerns. In follow-up analyses, each moral concern was found to be related to distinct patterns of relational, emotional, and social language. Our results are the first finding relating internally valid measures of moral concerns to observations of language, motivating several new avenues for exploring and investigating how the moral domain intersects with language usage.