Hate speech detection and racial bias mitigation in social media based on BERT model
Top Cited Papers
Open Access
- 27 August 2020
- journal article
- research article
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 15 (8) , e0237861
Abstract
Disparate biases associated with datasets and trained classifiers in hateful and abusive content identification tasks have raised many concerns recently. Although the problem of biased datasets on abusive language detection has been addressed more frequently, biases arising from trained classifiers have not yet been a matter of concern. In this paper, we first introduce a transfer learning approach for hate speech detection based on an existing pre-trained language model called BERT (Bidirectional Encoder Representations from Transformers) and evaluate the proposed model on two publicly available datasets that have been annotated for racism, sexism, hate or offensive content on Twitter. Next, we introduce a bias alleviation mechanism to mitigate the effect of bias in training set during the fine-tuning of our pre-trained BERT-based model for hate speech detection. Toward that end, we use an existing regularization method to reweight input samples, thereby decreasing the effects of high correlated training set’ s n-grams with class labels, and then fine-tune our pre-trained BERT-based model with the new re-weighted samples. To evaluate our bias alleviation mechanism, we employed a cross-domain approach in which we use the trained classifiers on the aforementioned datasets to predict the labels of two new datasets from Twitter, AAE-aligned and White-aligned groups, which indicate tweets written in African-American English (AAE) and Standard American English (SAE), respectively. The results show the existence of systematic racial bias in trained classifiers, as they tend to assign tweets written in AAE from AAE-aligned group to negative classes such as racism, sexism, hate, and offensive more often than tweets written in SAE from White-aligned group. However, the racial bias in our classifiers reduces significantly after our bias alleviation mechanism is incorporated. This work could institute the first step towards debiasing hate speech and abusive language detection systems.Keywords
All Related Versions
This publication has 25 references indexed in Scilit:
- One-step and Two-step Classification for Abusive Language Detection on Twitter2017
- Using Convolutional Neural Networks to Classify Hate-Speech2017
- Abusive Language Detection in Online User Content2016
- Demographic Dialectal Variation in Social Media: A Case Study of African-American English2016
- Do Characters Abuse More Than Words?2016
- Are You a Racist or Am I Seeing Things? Annotator Influence on Hate Speech Detection on Twitter2016
- Hateful Symbols or Hateful People? Predictive Features for Hate Speech Detection on Twitter2016
- Hate Speech Detection with Comment Embeddings2015
- Cyber Hate Speech on Twitter: An Application of Machine Classification and Statistical Modeling for Policy and Decision MakingPolicy & Internet, 2015
- Glove: Global Vectors for Word Representation2014