Mitigating Bias in Session-based Cyberbullying Detection: A Non-Compromising Approach

Lu Cheng, Ahmadreza Mosallanezhad, Yasin Silva, Deborah Hall, Huan Liu


Abstract
The element of repetition in cyberbullying behavior has directed recent computational studies toward detecting cyberbullying based on a social media session. In contrast to a single text, a session may consist of an initial post and an associated sequence of comments. Yet, emerging efforts to enhance the performance of session-based cyberbullying detection have largely overlooked unintended social biases in existing cyberbullying datasets. For example, a session containing certain demographic-identity terms (e.g., “gay” or “black”) is more likely to be classified as an instance of cyberbullying. In this paper, we first show evidence of such bias in models trained on sessions collected from different social media platforms (e.g., Instagram). We then propose a context-aware and model-agnostic debiasing strategy that leverages a reinforcement learning technique, without requiring any extra resources or annotations apart from a pre-defined set of sensitive triggers commonly used for identifying cyberbullying instances. Empirical evaluations show that the proposed strategy can simultaneously alleviate the impacts of the unintended biases and improve the detection performance.
Anthology ID:
2021.acl-long.168
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
August
Year:
2021
Address:
Online
Editors:
Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2158–2168
Language:
URL:
https://aclanthology.org/2021.acl-long.168
DOI:
10.18653/v1/2021.acl-long.168
Bibkey:
Cite (ACL):
Lu Cheng, Ahmadreza Mosallanezhad, Yasin Silva, Deborah Hall, and Huan Liu. 2021. Mitigating Bias in Session-based Cyberbullying Detection: A Non-Compromising Approach. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 2158–2168, Online. Association for Computational Linguistics.
Cite (Informal):
Mitigating Bias in Session-based Cyberbullying Detection: A Non-Compromising Approach (Cheng et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-long.168.pdf
Video:
 https://aclanthology.org/2021.acl-long.168.mp4
Code
 githublucheng/mitigatebiassessioncb