Moral disengagement is a mechanism whereby people distance or disconnect their actions from their moral evaluation. This work presents a novel knowledge graph schema, dataset, and transformer-based NLP model to identify and represent indicators of moral disengagement in text. Our graph schema is informed by Albert Bandura’s psychosocial mechanisms of moral disengagement, including dehumanization, victimization, moral condemnation and justification, and attribution (or displacement) of responsibility. Our preliminary dataset is comprised of online posts from five different communities. We present initial evidence that (1) our theory-based schema can represent moral disengagement indicators across these communities and (2) our transformer-based NLP model can identify indicators of moral disengagement in text. As it matures, this thread of computational social science research can help us understand the spread of morally-disengaged language and its effect on online communities.

Gender status, gender roles, and gender values vary widelyacross cultures. Anthropology has provided qualitative ac-counts of economic, cultural, and biological factors that im-pact social groups, and international organizations have gath-ered indices and surveys to help quantify gender inequalitiesin states. Concurrently, machine learning research has recentlycharacterized pervasive gender biases in AI language models,rooting from biases in their textual training data. While thesemachine biases produce sub-optimal inferences, they may helpus characterize and predict statistical gender gaps and gendervalues in the culture(s) that produced the training text, therebyhelping us understand cultural context through big data. Thispaper presents an approach to (1) construct word embeddings(i.e., vector-based lexical semantics) from a region’s social me-dia, (2) quantify gender bias in word embeddings, and (3)correlate biases with survey responses and statistical gendergaps in education, politics, economics, and health. We validatethis approach using 2018 Twitter data spanning 143 countriesand 51 U.S. territories, 23 international and 7 U.S. gender gapstatistics, and seven international survey results from the WorldValue Survey. Integrating these heterogeneous data across cul-tures is an important step toward understanding (1) how biasesin culture might manifest in machine learning models and (2)how to estimate gender inequality from big data.

Understanding the values, norms, behaviors, and causal beliefs of communities is a central goal of cognitive science, with practical benefits of grasping and improving community factors such as healthcare delivery. These cultural causal beliefs are evident, in part, within narratives, interview transcripts, ethnography, and other textual sources, but analyzing these texts presently involves tedious expert hand-coding or relatively shallow qualitative text analysis or classification. We present a novel approach for extracting graphical causal models from text via NLP, including qualitative causality, intentions, teleology, sentiment, welfare, social influence, and other rationale. The factors (i.e., nodes) of these causal models are tagged with ethnographic attributes and word-senses, allowing aggregation of causal models over thousands of passages to identify correlations and recurring themes. We apply this approach to a corpus of narrative interviews about maternal and child health and healthcare delivery in Bihar, India, corroborating the hand-coded results of human experts and also identifying novel insights about explanatory structure.