Cross-Domain Classification of Moral Values

Cross-Domain Classification of Moral Values

Liscio, E. (TU Delft Interactive Intelligence)
Dondera, Alin E. (Student TU Delft)
Geadau, Andrei (Student TU Delft)
Jonker, C.M. (TU Delft Interactive Intelligence)
Murukannaiah, P.K. (TU Delft Interactive Intelligence)

2022

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.

http://resolver.tudelft.nl/uuid:0386fae7-947f-43de-aaa1-aa9c164e85af

Association for Computational Linguistics (ACL)

9781955917766

Findings of the Association for Computational Linguistics: NAACL 2022 - Findings

2022 Findings of the Association for Computational Linguistics: NAACL 2022, 2022-07-10 → 2022-07-15, Seattle, United States

Findings of NAACL '22

Institutional Repository

conference paper

© 2022 E. Liscio, Alin E. Dondera, Andrei Geadau, C.M. Jonker, P.K. Murukannaiah