Morality Classification in Natural Language Text

The language employed by an individual when discussing topics of a moral nature (of the kind typically found in, e.g., social media) is revealing not only of the text affective contents itself, but also of the individual who wrote the text in the first place. Based on these observations, this work intends to illustrate how two kinds of morality-related information may be inferred from text by presenting a number of shallow and deep learning models of moral stance and moral foundations classification. In doing so, we introduce a novel corpus of texts labelled with moral foundation scores, and a novel approach to fine-grained, human-centric moral foundations classification that is, to the best of our knowledge, among the first NLP studies of this kind.