Towards Procedural Fairness: Uncovering Biases in How a Toxic Language Classifier Uses Sentiment Information

Isar Nejadgholi, Esma Balkir, Kathleen Fraser, Svetlana Kiritchenko


Abstract
Previous works on the fairness of toxic language classifiers compare the output of models with different identity terms as input features but do not consider the impact of other important concepts present in the context. Here, besides identity terms, we take into account high-level latent features learned by the classifier and investigate the interaction between these features and identity terms. For a multi-class toxic language classifier, we leverage a concept-based explanation framework to calculate the sensitivity of the model to the concept of sentiment, which has been used before as a salient feature for toxic language detection. Our results show that although for some classes, the classifier has learned the sentiment information as expected, this information is outweighed by the influence of identity terms as input features. This work is a step towards evaluating procedural fairness, where unfair processes lead to unfair outcomes. The produced knowledge can guide debiasing techniques to ensure that important concepts besides identity terms are well-represented in training datasets.
Anthology ID:
2022.blackboxnlp-1.18
Volume:
Proceedings of the Fifth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates (Hybrid)
Editors:
Jasmijn Bastings, Yonatan Belinkov, Yanai Elazar, Dieuwke Hupkes, Naomi Saphra, Sarah Wiegreffe
Venue:
BlackboxNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
225–237
Language:
URL:
https://aclanthology.org/2022.blackboxnlp-1.18
DOI:
10.18653/v1/2022.blackboxnlp-1.18
Bibkey:
Cite (ACL):
Isar Nejadgholi, Esma Balkir, Kathleen Fraser, and Svetlana Kiritchenko. 2022. Towards Procedural Fairness: Uncovering Biases in How a Toxic Language Classifier Uses Sentiment Information. In Proceedings of the Fifth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, pages 225–237, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.
Cite (Informal):
Towards Procedural Fairness: Uncovering Biases in How a Toxic Language Classifier Uses Sentiment Information (Nejadgholi et al., BlackboxNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.blackboxnlp-1.18.pdf