Skip to contents

Crowdsourced norms weighted along the five moral categories from Moral Foundations Theory. Rather than discrete, binary rankings of terms as either indicating a moral category or not, this dictionary weights a term as more-or-less related to a given moral category. These weights included the *probability* a term belongs to a moral foundation. The dictionary also includes the we obtained "the average sentiment score of the annotations in which the word appeared in a foundation-specific fashion." (Hopp et al. 2020). This determines whether a term is on the "virtue" or "vice" side of a given moral foundation category.

Usage

emfd_norms

Format

A data frame with 3,270 rows and 11 variables.

Source

https://github.com/medianeuroscience/emfdscore/tree/master/emfdscore/dictionaries

Variables

Variables:

  • term. unique word (only unigrams)

  • care_p. probability term belongs to care

  • fairness_p. probability term belongs to fairness

  • loyalty_p. probability term belongs to loyalty

  • authority_p. probability term belongs to authority

  • sanctity_p. probability term belongs to sanctity

  • care_sent. average sentiment of the care-specific context

  • fairness_sent. average sentiment of the fairness-specific context

  • loyalty_sent. average sentiment of the loyalty-specific context

  • authority_sent. average sentiment of the authority-specific context

  • sanctity_sent. average sentiment of the sanctity-specific context

References

Hopp, F. R., Fisher, J. T., Cornell, D., Huskey, R., & Weber, R. (2021). The extended Moral Foundations Dictionary (eMFD): Development and applications of a crowd-sourced approach to extracting moral intuitions from text.Behavior research methods, 53, 232-246.