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

Enrico Liscio, Oscar Araque, Lorenzo Gatti, Ionut Constantinescu, Catholijn Jonker, Kyriaki Kalimeri, Pradeep Kumar Murukannaiah


Abstract
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 thirty-five 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.
Anthology ID:
2023.acl-long.789
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
14113–14132
Language:
URL:
https://aclanthology.org/2023.acl-long.789
DOI:
10.18653/v1/2023.acl-long.789
Bibkey:
Cite (ACL):
Enrico Liscio, Oscar Araque, Lorenzo Gatti, Ionut Constantinescu, Catholijn Jonker, Kyriaki Kalimeri, and Pradeep Kumar Murukannaiah. 2023. What does a Text Classifier Learn about Morality? An Explainable Method for Cross-Domain Comparison of Moral Rhetoric. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 14113–14132, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
What does a Text Classifier Learn about Morality? An Explainable Method for Cross-Domain Comparison of Moral Rhetoric (Liscio et al., ACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.acl-long.789.pdf
Video:
 https://aclanthology.org/2023.acl-long.789.mp4