Stereotypical Bias Removal for Hate Speech Detection Task using Knowledge-based Generalizations

Abstract

With the ever-increasing cases of hate spread on social media platforms, it is critical to design abuse detection mechanisms to proactively avoid and control such incidents. While there exist methods for hate speech detection, they stereotype words and hence suffer from inherently biased training. Bias removal has been traditionally studied for structured datasets, but we aim at bias mitigation from unstructured text data. In this paper, we make two important contributions. First, we systematically design methods to quantify the bias for any model and propose algorithms for identifying the set of words which the model stereotypes. Second, we propose novel methods leveraging knowledge-based generalizations for bias-free learning. Knowledge-based generalization provides an effective way to encode knowledge because the abstraction they provide not only generalizes content but also facilitates retraction of information from the hate speech detection classifier, thereby reducing the imbalance. We experiment with multiple knowledge generalization policies and analyze their effect on general performance and in mitigating bias. Our experiments with two real-world datasets, a Wikipedia Talk Pages dataset (WikiDetox) of size ~96k and a Twitter dataset of size ~24k, show that the use of knowledge-based generalizations results in better performance by forcing the classifier to learn from generalized content. Our methods utilize existing knowledge-bases and can easily be extended to other tasks

References in corpus (8)

• Semantics derived automatically from language corpora contain human-like biases
• Equality of Opportunity in Supervised Learning
• Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
• Deep Learning for Hate Speech Detection in Tweets
• Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations
• Automated Hate Speech Detection and the Problem of Offensive Language
• On the (im)possibility of fairness
• Racial Disparity in Natural Language Processing: A Case Study of Social Media African-American English

Cited by in corpus (12)

• Hate Speech Detection and Racial Bias Mitigation in Social Media based on BERT model
• Representation Bias in Data: A Survey on Identification and Resolution Techniques
• Transfer Learning for Hate Speech Detection in Social Media
• SoK: Content Moderation in Social Media, from Guidelines to Enforcement, and Research to Practice
• Cyberbullying Detection with Fairness Constraints
• ALONE: A Dataset for Toxic Behavior among Adolescents on Twitter
• Towards generalisable hate speech detection: a review on obstacles and solutions
• Contrastive Learning for Fair Representations
• SWE2: SubWord Enriched and Significant Word Emphasized Framework for Hate Speech Detection
• An Effective, Robust and Fairness-aware Hate Speech Detection Framework
• An Information Retrieval Approach to Building Datasets for Hate Speech Detection
• Studying Socially Unacceptable Discourse Classification (SUD) through different eyes: "Are we on the same page ?"