Darkness can not drive out darkness: Investigating Bias in Hate SpeechDetection Models (2022.acl-srw)
Copied to clipboard
| Challenge: | a recent study shows that machine learning models are biased and they might make the wrong decisions for the wrong reasons. |
| Approach: | They investigate the impact of social bias on the performance of hate speech detection models . they also investigate the causal effect of intersectional bias on models' unfairness . |
| Outcome: | The proposed model is biased and makes the wrong decisions for the wrong reasons. |
Similar Papers
Mitigating Biases in Hate Speech Detection from A Causal Perspective (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to detect hate speech are prone to spurious correlations between training data and labels, which could lead to biased treatment of vulnerable and minority groups. |
| Approach: | They propose to use grammar induction to find grammar patterns for hate speech and analyze this phenomenon from a causal perspective. |
| Outcome: | The proposed methods can detect hate speech from a causal perspective and are robust to different datasets. |
The Risk of Racial Bias in Hate Speech Detection (P19-1)
Copied to clipboard
| Challenge: | Annotators’ insensitivity to differences in dialect can lead to racial bias in automatic hate speech detection models, potentially amplifying harm against minority populations. |
| Approach: | They propose *dialect* and *race priming* as ways to reduce the racial bias in hate speech detection models by detecting differences in dialects in annotated tweets. |
| Outcome: | The proposed models acquire and propagate these biases, such that AAE tweets and tweets by self-identified African Americans are up to two times more likely to be labelled as offensive compared to others. |
Robust Hate Speech Detection via Mitigating Spurious Correlations (2022.aacl-short)
Copied to clipboard
| Challenge: | a novel hate speech detection model can be used to detect word- and character-level adversarial attacks . existing adversarials assume that attackers replace the target words with other names to evade detection . |
| Approach: | They propose a robust hate speech detection model that can defend against adversarial attacks . they describe the process of hate speech recognition by a causal graph and a regularized entropy loss function to quantify spurious correlation . |
| Outcome: | The proposed model can defend against word- and character-level adversarial attacks. |
Comparative Evaluation of Label-Agnostic Selection Bias in Multilingual Hate Speech Datasets (2020.emnlp-main)
Copied to clipboard
| Challenge: | a recent study has shown that data collection is neglected by ignoring the quality of data. |
| Approach: | They propose to use latent semantics to evaluate selection bias in hate speech . they compare latent Dirichlet Allocation (LDA) to eleven hate speech corpora . |
| Outcome: | The proposed method could be revisable before focusing on classification performance. |
Reducing Gender Bias in Abusive Language Detection (D18-1)
Copied to clipboard
| Challenge: | Abusive language detection models tend to be biased toward identity words of a certain group of people . recent studies have raised concerns about the robustness of such systems . |
| Approach: | They propose to use debiased word embeddings, gender swap data augmentation to reduce model bias . they also propose to fine-tune models with a larger corpus to correct such bias if needed . |
| Outcome: | The proposed methods reduce model bias by 90-98% and can be extended to correct model bias in other scenarios. |
Toxic, Hateful, Offensive or Abusive? What Are We Really Classifying? An Empirical Analysis of Hate Speech Datasets (2020.lrec-1)
Copied to clipboard
| Challenge: | a recent study shows that many definitions are being used for equivalent concepts, making most datasets incompatible. |
| Approach: | They analyze six publicly available datasets to determine their similarity and compatibility . they propose to use Fast Text word vectors to analyze similarity between different datasets . |
| Outcome: | The proposed model performs better on similar datasets and worse on more non-offensive samples. |
Mind Your Bias: A Critical Review of Bias Detection Methods for Contextual Language Models (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for detection of biases in contextual language models are inconsistent and inconclusive. |
| Approach: | They propose to use word embedding association test to detect biases in contextual language models to compare them with other methods. |
| Outcome: | The proposed methods are inconsistent and inconclusive for language models with word embeddings. |
Bias and Fairness in Natural Language Processing (D19-2)
Copied to clipboard
| Challenge: | a tutorial will review the history of bias and fairness studies in machine learning and language processing . |
| Approach: | This tutorial reviews the history of bias and fairness studies in machine learning and language processing . it presents recent community effort to quantify and mitigat bias in natural language processing models . |
| Outcome: | This tutorial reviews the history of bias and fairness studies in machine learning and language processing . it aims to quantify and mitigate bias in natural language processing models for a wide spectrum of tasks . |
HateDay: Insights from a Global Hate Speech Dataset Representative of a Day on Twitter (2025.acl-long)
Copied to clipboard
Manuel Tonneau, Diyi Liu, Niyati Malhotra, Scott A. Hale, Samuel Fraiberger, Victor Orozco-Olvera, Paul Röttger
| Challenge: | Prior work on automated hate speech detection models has been limited due to systematic biases in evaluation datasets and poor performance across geographies. |
| Approach: | They propose to construct a global hate speech dataset representative of social media settings from tweets posted on September 21, 2022. |
| Outcome: | The proposed dataset covers eight languages and four English-speaking countries and covers eight countries where English is the main language on Twitter. |
Detection of Abusive Language: the Problem of Biased Datasets (N19-1)
Copied to clipboard
| Challenge: | Recent studies have reported high classification performance on datasets with difficult cases of abusive language. |
| Approach: | They examine the impact of data bias on abusive language detection by focusing on specific microposts rather than random sampling. |
| Outcome: | The proposed method is more accurate and more accurate than random sampling. |