Cross-Domain Classification of Moral Values

Enrico Liscio, Alin Dondera, Andrei Geadau, Catholijn Jonker, Pradeep Murukannaiah


Abstract
Moral values influence how we interpret and act upon the information we receive. Identifying human moral values is essential for artificially intelligent agents to co-exist with humans. Recent progress in natural language processing allows the identification of moral values in textual discourse. However, domain-specific moral rhetoric poses challenges for transferring knowledge from one domain to another.We provide the first extensive investigation on the effects of cross-domain classification of moral values from text. We compare a state-of-the-art deep learning model (BERT) in seven domains and four cross-domain settings. We show that a value classifier can generalize and transfer knowledge to novel domains, but it can introduce catastrophic forgetting. We also highlight the typical classification errors in cross-domain value classification and compare the model predictions to the annotators agreement. Our results provide insights to computer and social scientists that seek to identify moral rhetoric specific to a domain of discourse.
Anthology ID:
2022.findings-naacl.209
Volume:
Findings of the Association for Computational Linguistics: NAACL 2022
Month:
July
Year:
2022
Address:
Seattle, United States
Venues:
Findings | NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2727–2745
Language:
URL:
https://aclanthology.org/2022.findings-naacl.209
DOI:
10.18653/v1/2022.findings-naacl.209
Bibkey:
Cite (ACL):
Enrico Liscio, Alin Dondera, Andrei Geadau, Catholijn Jonker, and Pradeep Murukannaiah. 2022. Cross-Domain Classification of Moral Values. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 2727–2745, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Cross-Domain Classification of Moral Values (Liscio et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-naacl.209.pdf
Software:
 2022.findings-naacl.209.software.zip
Code
 adondera/transferability-of-values
Data
ETHICS