Abstract
Text classification enables higher efficiency on text data queries in information retrieval. However, unintended demographic bias can impair text toxicity classification. Thus, we propose a novel debiasing framework utilizing Adversarial Learning on word embeddings of multi-class sensitive demographic words to alleviate this bias. Slight adjustment over word embeddings with flipped sensitive indices is achieved, and the modified word embeddings are used in the downstream classification task to realize Demographic Parity. The experimental results validate the effectiveness of our proposed method in mitigating multi-class unintended demographic bias without impairing the original classification accuracy.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Dixon, L., Li, J., Sorensen, J., Thain, N., Vasserman, L.: Measuring and mitigating unintended bias in text classification. In: Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society, pp. 67–73 (2018)
Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, vol. 27 (2014)
Kang, Q., Yao, S., Zhou, M., Zhang, K., Abusorrah, A.: Effective visual domain adaptation via generative adversarial distribution matching. IEEE Trans. Neural Netw. Learn. Syst. 32(9), 3919–3929 (2021). https://doi.org/10.1109/TNNLS.2020.3016180
Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 (2013)
Park, J.H., Shin, J., Fung, P.: Reducing gender bias in abusive language detection. arXiv preprint arXiv:1808.07231 (2018)
Pennington, J., Socher, R., Manning, C.D.: Glove: global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1532–1543 (2014)
Sweeney, C., Najafian, M.: Reducing sentiment polarity for demographic attributes in word embeddings using adversarial learning. In: Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, pp. 359–368 (2020)
Zhang, B.H., Lemoine, B., Mitchell, M.: Mitigating unwanted biases with adversarial learning. In: Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society, pp. 335–340 (2018)
Zhang, G., Bai, B., Zhang, J., Bai, K., Zhu, C., Zhao, T.: Demographics should not be the reason of toxicity: mitigating discrimination in text classifications with instance weighting. arXiv preprint arXiv:2004.14088 (2020)
Zhou, G., Yao, L., Xu, X., Wang, C., Zhu, L.: Cycle-balanced representation learning for counterfactual inference. arXiv preprint arXiv:2110.15484 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Pan, L., Yao, L., Zhang, W., Wang, X. (2022). Mitigating Multi-class Unintended Demographic Bias in Text Classification with Adversarial Learning. In: Chbeir, R., Huang, H., Silvestri, F., Manolopoulos, Y., Zhang, Y. (eds) Web Information Systems Engineering – WISE 2022. WISE 2022. Lecture Notes in Computer Science, vol 13724. Springer, Cham. https://doi.org/10.1007/978-3-031-20891-1_27
Download citation
DOI: https://doi.org/10.1007/978-3-031-20891-1_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20890-4
Online ISBN: 978-3-031-20891-1
eBook Packages: Computer ScienceComputer Science (R0)