Addressing Biases in the Texts using an End-to-End Pipeline Approach
Not on the map. Why?
Abstract (arXiv)
The concept of fairness is gaining popularity in academia and industry. Social media is especially vulnerable to media biases and toxic language and comments. We propose a fair ML pipeline that takes a text as input and determines whether it contains biases and toxic content. Then, based on pre-trained word embeddings, it suggests a set of new words by substituting the bi-ased words, the idea is to lessen the effects of those biases by replacing them with alternative words. We compare our approach to existing fairness models to determine its effectiveness. The results show that our proposed pipeline can de-tect, identify, and mitigate biases in social media data
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 13 of its 31 references that are in the map. First posted on arXiv 13 Mar 2023.
Builds on
13 of 31 references.
References · 13
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
- 2017Counterfactual Fairnesscited by 802
- 2018Mitigating Unwanted Biases with Adversarial Learningcited by 663
- 2017On Fairness and Calibrationcited by 406
- 2019Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classificationcited by 396
- 2018Classification with Fairness Constraints: A Meta-Algorithm with Provable Guaranteescited by 146
- 2018Aequitas: A Bias and Fairness Audit Toolkitcited by 145
- 2019On the Fairness of Disentangled Representationscited by 144
- 2014word2vec Explained: deriving Mikolov et al.'s negative-sampling word-embedding methodcited by 109
- 2022A Survey on the Fairness of Recommender Systemscited by 102
- 2018Fairness GANcited by 32
- 2017Themis-ml: A Fairness-aware Machine Learning Interface for End-to-end Discrimination Discovery and Mitigationcited by 24
1 more
- 2021Dictionary-based Debiasing of Pre-trained Word Embeddingscited by 24
Built on by
Citing papers per year: 2025: 1.
1 paper.