Reducing Gender Bias in Abusive Language Detection
Abusive language detection models tend to have a problem of being biased toward identity words of a certain group of people because of imbalanced training datasets. For example, "You are a good woman" was considered "sexist" when trained on an existing dataset. Such model bias is an obstacle for models to be robust enough for practical use. In this work, we measure gender biases on models trained with different abusive language datasets, while analyzing the effect of different pre-trained word embeddings and model architectures. We also experiment with three bias mitigation methods: (1) debiased word embeddings, (2) gender swap data augmentation, and (3) fine-tuning with a larger corpus. These methods can effectively reduce gender bias by 90-98% and can be extended to correct model bias in other scenarios.
Code (0)
등록된 구현이 없습니다.
Tasks
Abusive LanguageData AugmentationWord EmbeddingsSimilar Papers 제목 키워드 기반
Fine-Grained Fairness Analysis of Abusive Language Detection Systems with CheckList
Current abusive language detection systems have demonstrated unintended bias towards sensitive features such as nationality or gender. This is a crucial issue, which may harm minorities and underrepresented groups if suc…
Abusive LanguageFairnessIntersectional Bias in Hate Speech and Abusive Language Datasets
Algorithms are widely applied to detect hate speech and abusive language in social media. We investigated whether the human-annotated data used to train these algorithms are biased. We utilized a publicly available annot…
Abuse DetectionAbusive LanguageExamining Temporal Bias in Abusive Language Detection
The use of abusive language online has become an increasingly pervasive problem that damages both individuals and society, with effects ranging from psychological harm right through to escalation to real-life violence an…
Abusive LanguageInvestigating Sampling Bias in Abusive Language Detection
Abusive language detection is becoming increasingly important, but we still understand little about the biases in our datasets for abusive language detection, and how these biases affect the quality of abusive language d…
Abusive LanguageRacial Bias in Hate Speech and Abusive Language Detection Datasets
Technologies for abusive language detection are being developed and applied with little consideration of their potential biases. We examine racial bias in five different sets of Twitter data annotated for hate speech and…
Abuse DetectionAbusive Language