LibertyMFD: A Lexicon to Assess the Moral Foundation of Liberty.

Araque, Óscar; Gatti, Lorenzo; Kalimeri, Kyriaki

doi:10.1145/3524458.3547264

Cited by 4 publications

(1 citation statement)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We choose the MFT because Morality Classification Classification of moral elements in text has been approached via moral lexicons, lists of words depictive of moral elements. Lexicons are generated manually (Graham et al, 2009;Schwartz, 2012), via semi-automated methods (Wilson et al, 2018;Araque et al, 2020), or expanding a seed list with NLP techniques (Ponizovskiy et al, 2020;Araque et al, 2022). The lexicons are then used to classify morality using text similarity (Bahgat et al, 2020;Pavan et al, 2020).…”

Section: Moral Theoriesmentioning

confidence: 99%

What does a Text Classifier Learn about Morality? An Explainable Method for Cross-Domain Comparison of Moral Rhetoric

Liscio¹,

Araque²,

Gatti³

et al. 2023

Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

View full text Add to dashboard Cite

Moral rhetoric influences our judgement. Although social scientists recognize moral expression as domain specific, there are no systematic methods for analyzing whether a text classifier learns the domain-specific expression of moral language or not. We propose Tomea, a method to compare a supervised classifier's representation of moral rhetoric across domains. Tomea enables quantitative and qualitative comparisons of moral rhetoric via an interpretable exploration of similarities and differences across moral concepts and domains. We apply Tomea on moral narratives in thirtyfive thousand tweets from seven domains. We extensively evaluate the method via a crowd study, a series of cross-domain moral classification comparisons, and a qualitative analysis of cross-domain moral expression.

show abstract